arXiv subjects

Ron Bitton

Publications and source records attributed to Ron Bitton.

At least 19 recordsLinked to original sources

arXiv2026

Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)

The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages and Model Context Protocol (MCP) tool calls. Prior work identified replay and prompt-injection attacks in AP2 v0.1. AP2 v0.2 addresses some of these issues but adds capabilities and deployment assumptions that require renewed analysis. We present a systematic security analysis of AP2 v0.2 based on its roles, transaction lifecycle, deployment architectures, and trust boundaries. We divide the lifecycle into five phases and identify five deployment architectures. Using MAESTRO (Multi-Agent Environment, Security, Threat, Risk, Outcome), we model four threat actors, eleven attack surfaces, eighteen adversary capabilities, and six attacker goals. The resulting catalog contains 48 threats spanning five attack families. We score these threats with the Artificial Intelligence Vulnerability Scoring System (AIVSS), identifying eight that reach the High band in at least one architecture. Because no complete public AP2 deployment was available, we build a testbed spanning all five architectures and develop five proof-of-concept demonstrations covering all eight High-risk threats and their mitigations. We also develop a deployment-aware scanner that maps applicable threats to static, cross-role consistency, and adversarial checks. Our analysis shows that valid mandate signatures alone do not ensure that an agent-mediated transaction reflects the user's intent when its pre-authorization context is manipulated.

cs.CR↗

arXiv2026

Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting

The growing adoption of agentic LLM applications has introduced a new threat previously named as promptware. While prior work has established that adversaries can exploit direct channels to LLM applications to apply promptware under weak threat models, many applications do not provide any direct channels that could be exploited for prompt injection beyond the Internet. This raises a question: can attackers exploit LLM applications at scale without any direct channels in practical threat models? In this work, we show that the inherent tendency of LLMs to hallucinate resource identifiers can be exploited to amplify untargeted promptware attacks that pull adversarial prompts at scale and could be exploited to establish a botnet. We introduce adversarial hallucination squatting, a technique in which attackers identify trending resources (e.g., popular repositories, popular skills, etc.), compute the LLM distribution of hallucinations on the trending resource names, and preemptively register them to host adversarial prompts. By leveraging the predictability and transferability of hallucinations across foundational LLMs and to application layers, adversaries can significantly amplify the reach of untargeted promptware under weak threat models and establish a botnet by exploiting LLM applications to install a bot on the device that pulled the compromised hallucinated resource from the Inter. We empirically demonstrate that hallucinated resource generation occurs at high rates, up to 85% in repository cloning scenarios and up to 100% in skill installation, and that these hallucinations transfer between foundational models and different prompts. We demonstrate the practicality of adversarial hallucination squatting against various production LLM applications with integrated terminals in their set of tools, achieving remote tool execution and remote code execution.

cs.CR↗

arXiv2026

ConGISATA: A Framework for Continuous Gamified Information Security Awareness Training and Assessment

The incidence of cybersecurity attacks utilizing social engineering techniques has increased. Such attacks exploit the fact that in every secure system, there is at least one individual with the means to access sensitive information. Since it is easier to deceive a person than it is to bypass the defense mechanisms in place, these types of attacks have gained popularity. This situation is exacerbated by the fact that people are more likely to take risks in their passive form, i.e., risks that arise due to the failure to perform an action. Passive risk has been identified as a significant threat to cybersecurity. To address these threats, there is a need to strengthen individuals' information security awareness (ISA). Therefore, we developed ConGISATA - a continuous gamified ISA training and assessment framework based on embedded mobile sensors; a taxonomy for evaluating mobile users' security awareness served as the basis for the sensors' design. ConGISATA's continuous and gradual training process enables users to learn from their real-life mistakes and adapt their behavior accordingly. ConGISATA aims to transform passive risk situations (as perceived by an individual) into active risk situations, as people tend to underestimate the potential impact of passive risks. Our evaluation of the proposed framework demonstrates its ability to improve individuals' ISA, as assessed by the sensors and in simulations of common attack vectors.

cs.CR↗

arXiv2025

ASTRA: Agentic Steerability and Risk Assessment Framework

Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via connected tools. This capability introduces significant risks that go far beyond those of harmful text presented in a chatbot that was the main application of LLMs. A compromised AI agent can deliberately abuse powerful tools to perform malicious actions, in many cases irreversible, and limited solely by the guardrails on the tools themselves and the LLM ability to enforce them. This paper presents ASTRA, a first-of-its-kind framework designed to evaluate the effectiveness of LLMs in supporting the creation of secure agents that enforce custom guardrails defined at the system-prompt level (e.g., "Do not send an email out of the company domain," or "Never extend the robotic arm in more than 2 meters"). Our holistic framework simulates 10 diverse autonomous agents varying between a coding assistant and a delivery drone equipped with 37 unique tools. We test these agents against a suite of novel attacks developed specifically for agentic threats, inspired by the OWASP Top 10 but adapted to challenge the ability of the LLM for policy enforcement during multi-turn planning and execution of strict tool activation. By evaluating 13 open-source, tool-calling LLMs, we uncovered surprising and significant differences in their ability to remain secure and keep operating within their boundaries. The purpose of this work is to provide the community with a robust and unified methodology to build and validate better LLMs, ultimately pushing for more secure and reliable agentic AI systems.

cs.CR↗

arXiv2025

Security Steerability is All You Need

The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate the GenAI related security threats by developing evaluation methods and designing defenses. However, while most of the GenAI security work focuses on universal threats (e.g. 'How to build a bomb'), there is significantly less discussion on application-level security and how to evaluate and mitigate it. Thus, in this work we adopt an application-centric approach to GenAI security, and show that while LLMs cannot protect against ad-hoc application specific threats, they can provide the framework for applications to protect themselves against such threats. Our first contribution is defining Security Steerability - a novel security measure for LLMs, assessing the model's capability to adhere to strict guardrails that are defined in the system prompt (e.g. 'Refrain from discussing about our competitors'). These guardrails, in case effective, can stop threats in the presence of malicious users who attempt to circumvent the application purpose. Our second contribution is a methodology to measure the security steerability of LLMs, utilizing a newly-developed benchmark called VeganRibs which assesses the LLM behavior in forcing specific guardrails that are not security per-se, in the presence of malicious user that tries to bypass the guardrails through prompt injection attacks with attack boosters (jailbreaks and perturbations). Using the new benchmark, we analyzed 18 open-source LLMs, demonstrating significant differences between their security steerability that are not trivial to foresee...

cs.CR↗

arXiv2024

Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking

In this paper, we show that with the ability to jailbreak a GenAI model, attackers can escalate the outcome of attacks against RAG-based GenAI-powered applications in severity and scale. In the first part of the paper, we show that attackers can escalate RAG membership inference attacks and RAG entity extraction attacks to RAG documents extraction attacks, forcing a more severe outcome compared to existing attacks. We evaluate the results obtained from three extraction methods, the influence of the type and the size of five embeddings algorithms employed, the size of the provided context, and the GenAI engine. We show that attackers can extract 80%-99.8% of the data stored in the database used by the RAG of a Q&A chatbot. In the second part of the paper, we show that attackers can escalate the scale of RAG data poisoning attacks from compromising a single GenAI-powered application to compromising the entire GenAI ecosystem, forcing a greater scale of damage. This is done by crafting an adversarial self-replicating prompt that triggers a chain reaction of a computer worm within the ecosystem and forces each affected application to perform a malicious activity and compromise the RAG of additional applications. We evaluate the performance of the worm in creating a chain of confidential data extraction about users within a GenAI ecosystem of GenAI-powered email assistants and analyze how the performance of the worm is affected by the size of the context, the adversarial self-replicating prompt used, the type and size of the embeddings algorithm employed, and the number of hops in the propagation. Finally, we review and analyze guardrails to protect RAG-based inference and discuss the tradeoffs.

cs.CR↗

arXiv2024

A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares

In this paper we argue that a jailbroken GenAI model can cause substantial harm to GenAI-powered applications and facilitate PromptWare, a new type of attack that flips the GenAI model's behavior from serving an application to attacking it. PromptWare exploits user inputs to jailbreak a GenAI model to force/perform malicious activity within the context of a GenAI-powered application. First, we introduce a naive implementation of PromptWare that behaves as malware that targets Plan & Execute architectures (a.k.a., ReAct, function calling). We show that attackers could force a desired execution flow by creating a user input that produces desired outputs given that the logic of the GenAI-powered application is known to attackers. We demonstrate the application of a DoS attack that triggers the execution of a GenAI-powered assistant to enter an infinite loop that wastes money and computational resources on redundant API calls to a GenAI engine, preventing the application from providing service to a user. Next, we introduce a more sophisticated implementation of PromptWare that we name Advanced PromptWare Threat (APwT) that targets GenAI-powered applications whose logic is unknown to attackers. We show that attackers could create user input that exploits the GenAI engine's advanced AI capabilities to launch a kill chain in inference time consisting of six steps intended to escalate privileges, analyze the application's context, identify valuable assets, reason possible malicious activities, decide on one of them, and execute it. We demonstrate the application of APwT against a GenAI-powered e-commerce chatbot and show that it can trigger the modification of SQL tables, potentially leading to unauthorized discounts on the items sold to the user.

cs.CR↗

arXiv2024

Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

In this paper, we show that when the communication between GenAI-powered applications relies on RAG-based inference, an attacker can initiate a computer worm-like chain reaction that we call Morris-II. This is done by crafting an adversarial self-replicating prompt that triggers a cascade of indirect prompt injections within the ecosystem and forces each affected application to perform malicious actions and compromise the RAG of additional applications. We evaluate the performance of the worm in creating a chain of confidential user data extraction within a GenAI ecosystem of GenAI-powered email assistants and analyze how the performance of the worm is affected by the size of the context, the adversarial self-replicating prompt used, the type and size of the embedding algorithm employed, and the number of hops in the propagation. Finally, we introduce the Virtual Donkey, a guardrail intended to detect and prevent the propagation of Morris-II with minimal latency, high accuracy, and a low false-positive rate. We evaluate the guardrail's performance and show that it yields a perfect true-positive rate of 1.0 with a false-positive rate of 0.015, and is robust against out-of-distribution worms, consisting of unseen jailbreaking commands, a different email dataset, and various worm usecases.

cs.CR↗

arXiv2023

The Adversarial Implications of Variable-Time Inference

Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess the ability to query the model and observe its outputs (e.g., labels). In this work, we demonstrate, for the first time, the ability to enhance such decision-based attacks. To accomplish this, we present an approach that exploits a novel side channel in which the adversary simply measures the execution time of the algorithm used to post-process the predictions of the ML model under attack. The leakage of inference-state elements into algorithmic timing side channels has never been studied before, and we have found that it can contain rich information that facilitates superior timing attacks that significantly outperform attacks based solely on label outputs. In a case study, we investigate leakage from the non-maximum suppression (NMS) algorithm, which plays a crucial role in the operation of object detectors. In our examination of the timing side-channel vulnerabilities associated with this algorithm, we identified the potential to enhance decision-based attacks. We demonstrate attacks against the YOLOv3 detector, leveraging the timing leakage to successfully evade object detection using adversarial examples, and perform dataset inference. Our experiments show that our adversarial examples exhibit superior perturbation quality compared to a decision-based attack. In addition, we present a new threat model in which dataset inference based solely on timing leakage is performed. To address the timing leakage vulnerability inherent in the NMS algorithm, we explore the potential and limitations of implementing constant-time inference passes as a mitigation strategy.

cs.CR↗

arXiv2023

D-Score: An Expert-Based Method for Assessing the Detectability of IoT-Related Cyber-Attacks

IoT devices are known to be vulnerable to various cyber-attacks, such as data exfiltration and the execution of flooding attacks as part of a DDoS attack. When it comes to detecting such attacks using network traffic analysis, it has been shown that some attack scenarios are not always equally easy to detect if they involve different IoT models. That is, when targeted at some IoT models, a given attack can be detected rather accurately, while when targeted at others the same attack may result in too many false alarms. In this research, we attempt to explain this variability of IoT attack detectability and devise a risk assessment method capable of addressing a key question: how easy is it for an anomaly-based network intrusion detection system to detect a given cyber-attack involving a specific IoT model? In the process of addressing this question we (a) investigate the predictability of IoT network traffic, (b) present a novel taxonomy for IoT attack detection which also encapsulates traffic predictability aspects, (c) propose an expert-based attack detectability estimation method which uses this taxonomy to derive a detectability score (termed `D-Score') for a given combination of IoT model and attack scenario, and (d) empirically evaluate our method while comparing it with a data-driven method.

cs.CR↗

arXiv2022

Latent SHAP: Toward Practical Human-Interpretable Explanations

Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks. However, since complex classification models produce superior performance when trained on low-level (or encoded) features, in many cases, the explanations generated by these algorithms are neither interpretable nor usable by humans. Methods proposed in recent studies that support the generation of human-interpretable explanations are impractical, because they require a fully invertible transformation function that maps the model's input features to the human-interpretable features. In this work, we introduce Latent SHAP, a black-box feature attribution framework that provides human-interpretable explanations, without the requirement for a fully invertible transformation function. We demonstrate Latent SHAP's effectiveness using (1) a controlled experiment where invertible transformation functions are available, which enables robust quantitative evaluation of our method, and (2) celebrity attractiveness classification (using the CelebA dataset) where invertible transformation functions are not available, which enables thorough qualitative evaluation of our method.

cs.LG↗

arXiv2022

Improving Interpretability via Regularization of Neural Activation Sensitivity

State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about the security and generalization of DNNs in real-world conditions, whereas the latter impedes users' trust in their output. In this research, we (1) examine the effect of adversarial robustness on interpretability and (2) present a novel approach for improving the interpretability of DNNs that is based on regularization of neural activation sensitivity. We evaluate the interpretability of models trained using our method to that of standard models and models trained using state-of-the-art adversarial robustness techniques. Our results show that adversarially robust models are superior to standard models and that models trained using our proposed method are even better than adversarially robust models in terms of interpretability.

cs.LG↗

arXiv2022

Attacking Object Detector Using A Universal Targeted Label-Switch Patch

Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predictions by placing a patch containing an adversarial pattern on the target object or anywhere within the frame. However, none of prior research proposed a misclassification attack on ODs, in which the patch is applied on the target object. In this study, we propose a novel, universal, targeted, label-switch attack against the state-of-the-art object detector, YOLO. In our attack, we use (i) a tailored projection function to enable the placement of the adversarial patch on multiple target objects in the image (e.g., cars), each of which may be located a different distance away from the camera or have a different view angle relative to the camera, and (ii) a unique loss function capable of changing the label of the attacked objects. The proposed universal patch, which is trained in the digital domain, is transferable to the physical domain. We performed an extensive evaluation using different types of object detectors, different video streams captured by different cameras, and various target classes, and evaluated different configurations of the adversarial patch in the physical domain.

cs.LG↗

arXiv2022

Evaluating the Security of Aircraft Systems

The sophistication and complexity of cyber attacks and the variety of targeted platforms have been growing in recent years. Various adversaries are abusing an increasing range of platforms, e.g., enterprise platforms, mobile phones, PCs, transportation systems, and industrial control systems. In recent years, we have witnessed various cyber attacks on transportation systems, including attacks on ports, airports, and trains. It is only a matter of time before transportation systems become a more common target of cyber attackers. Due to the enormous potential damage inherent in attacking vehicles carrying many passengers and the lack of security measures applied in traditional airborne systems, the vulnerability of aircraft systems is one of the most concerning topics in the vehicle security domain. This paper provides a comprehensive review of aircraft systems and components and their various networks, emphasizing the cyber threats they are exposed to and the impact of a cyber attack on these components and networks and the essential capabilities of the aircraft. In addition, we present a comprehensive and in-depth taxonomy that standardizes the knowledge and understanding of cyber security in the avionics field from an adversary's perspective. The taxonomy divides techniques into relevant categories (tactics) reflecting the various phases of the adversarial attack lifecycle and maps existing attacks according to the MITRE ATT&CK methodology. Furthermore, we analyze the security risks among the various systems according to the potential threat actors and categorize the threats based on STRIDE threat model. Future work directions are presented as guidelines for industry and academia.

cs.CR↗

arXiv2022

Evaluating the Security of Open Radio Access Networks

The Open Radio Access Network (O-RAN) is a promising RAN architecture, aimed at reshaping the RAN industry toward an open, adaptive, and intelligent RAN. In this paper, we conducted a comprehensive security analysis of Open Radio Access Networks (O-RAN). Specifically, we review the architectural blueprint designed by the O-RAN alliance -- A leading force in the cellular ecosystem. Within the security analysis, we provide a detailed overview of the O-RAN architecture; present an ontology for evaluating the security of a system, which is currently at an early development stage; detect the primary risk areas to O-RAN; enumerate the various threat actors to O-RAN; and model potential threats to O-RAN. The significance of this work is providing an updated attack surface to cellular network operators. Based on the attack surface, cellular network operators can carefully deploy the appropriate countermeasure for increasing the security of O-RAN.

cs.CR↗

arXiv2022

Adversarial Machine Learning Threat Analysis and Remediation in Open Radio Access Network (O-RAN)

O-RAN is a new, open, adaptive, and intelligent RAN architecture. Motivated by the success of artificial intelligence in other domains, O-RAN strives to leverage machine learning (ML) to automatically and efficiently manage network resources in diverse use cases such as traffic steering, quality of experience prediction, and anomaly detection. Unfortunately, it has been shown that ML-based systems are vulnerable to an attack technique referred to as adversarial machine learning (AML). This special kind of attack has already been demonstrated in recent studies and in multiple domains. In this paper, we present a systematic AML threat analysis for O-RAN. We start by reviewing relevant ML use cases and analyzing the different ML workflow deployment scenarios in O-RAN. Then, we define the threat model, identifying potential adversaries, enumerating their adversarial capabilities, and analyzing their main goals. Next, we explore the various AML threats associated with O-RAN and review a large number of attacks that can be performed to realize these threats and demonstrate an AML attack on a traffic steering model. In addition, we analyze and propose various AML countermeasures for mitigating the identified threats. Finally, based on the identified AML threats and countermeasures, we present a methodology and a tool for performing risk assessment for AML attacks for a specific ML use case in O-RAN.

cs.CR↗

arXiv2021

On The Vulnerability of Anti-Malware Solutions to DNS Attacks

Anti-malware agents typically communicate with their remote services to share information about suspicious files. These remote services use their up-to-date information and global context (view) to help classify the files and instruct their agents to take a predetermined action (e.g., delete or quarantine). In this study, we provide a security analysis of a specific form of communication between anti-malware agents and their services, which takes place entirely over the insecure DNS protocol. These services, which we denote DNS anti-malware list (DNSAML) services, affect the classification of files scanned by anti-malware agents, therefore potentially putting their consumers at risk due to known integrity and confidentiality flaws of the DNS protocol. By analyzing a large-scale DNS traffic dataset made available to the authors by a well-known CDN provider, we identify anti-malware solutions that seem to make use of DNSAML services. We found that these solutions, deployed on almost three million machines worldwide, exchange hundreds of millions of DNS requests daily. These requests are carrying sensitive file scan information, oftentimes - as we demonstrate - without any additional safeguards to compensate for the insecurities of the DNS protocol. As a result, these anti-malware solutions that use DNSAML are made vulnerable to DNS attacks. For instance, an attacker capable of tampering with DNS queries, gains the ability to alter the classification of scanned files, without presence on the scanning machine. We showcase three attacks applicable to at least three anti-malware solutions that could result in the disclosure of sensitive information and improper behavior of the anti-malware agent, such as ignoring detected threats. Finally, we propose and review a set of countermeasures for anti-malware solution providers to prevent the attacks stemming from the use of DNSAML services.

cs.CR↗

arXiv2021

Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems

Although cyberattacks on machine learning (ML) production systems can be harmful, today, security practitioners are ill equipped, lacking methodologies and tactical tools that would allow them to analyze the security risks of their ML-based systems. In this paper, we performed a comprehensive threat analysis of ML production systems. In this analysis, we follow the ontology presented by NIST for evaluating enterprise network security risk and apply it to ML-based production systems. Specifically, we (1) enumerate the assets of a typical ML production system, (2) describe the threat model (i.e., potential adversaries, their capabilities, and their main goal), (3) identify the various threats to ML systems, and (4) review a large number of attacks, demonstrated in previous studies, which can realize these threats. In addition, to quantify the risk of adversarial machine learning (AML) threat, we introduce a novel scoring system, which assign a severity score to different AML attacks. The proposed scoring system utilizes the analytic hierarchy process (AHP) for ranking, with the assistance of security experts, various attributes of the attacks. Finally, we developed an extension to the MulVAL attack graph generation and analysis framework to incorporate cyberattacks on ML production systems. Using the extension, security practitioners can apply attack graph analysis methods in environments that include ML components; thus, providing security practitioners with a methodological and practical tool for evaluating the impact and quantifying the risk of a cyberattack targeting an ML production system.

cs.CR↗