Search arXiv⌕ Search

arXiv subjects

Ben Nassi

Publications and source records attributed to Ben Nassi.

At least 19 recordsLinked to original sources
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

The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism

Prompt injection was initially framed as the large language model (LLM) analogue of SQL injection. However, over the past three years, attacks labeled as prompt injection have evolved from isolated input-manipulation exploits into multistep attack mechanisms that resemble malware. In this paper, we argue that prompt injections evolved into promptware, a new class of malware execution mechanism triggered through prompts engineered to exploit an application's LLM. We introduce a seven-stage promptware kill chain: Initial Access (prompt injection), Privilege Escalation (jailbreaking), Reconnaissance, Persistence (memory and retrieval poisoning), Command and Control, Lateral Movement, and Actions on Objective. We analyze thirty-six prominent studies and real-world incidents affecting production LLM systems and show that at least twenty-one documented attacks that traverse four or more stages of this kill chain, demonstrating that the threat model is not merely theoretical. We discuss the need for a defense-in-depth approach that addresses all stages of the promptware life cycle and review relevant countermeasures for each step. By moving the conversation from prompt injection to a promptware kill chain, our work provides analytical clarity, enables structured risk assessment, and lays a foundation for systematic security engineering of LLM-based systems.

cs.CR↗
arXiv2025

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous

The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware - maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these applications. While prior research warned about a potential shift in the threat landscape for LLM-powered applications, the risk posed by Promptware is frequently perceived as low. In this paper, we investigate the risk Promptware poses to users of Gemini-powered assistants (web application, mobile application, and Google Assistant). We propose a novel Threat Analysis and Risk Assessment (TARA) framework to assess Promptware risks for end users. Our analysis focuses on a new variant of Promptware called Targeted Promptware Attacks, which leverage indirect prompt injection via common user interactions such as emails, calendar invitations, and shared documents. We demonstrate 14 attack scenarios applied against Gemini-powered assistants across five identified threat classes: Short-term Context Poisoning, Permanent Memory Poisoning, Tool Misuse, Automatic Agent Invocation, and Automatic App Invocation. These attacks highlight both digital and physical consequences, including spamming, phishing, disinformation campaigns, data exfiltration, unapproved user video streaming, and control of home automation devices. We reveal Promptware's potential for on-device lateral movement, escaping the boundaries of the LLM-powered application, to trigger malicious actions using a device's applications. Our TARA reveals that 73% of the analyzed threats pose High-Critical risk to end users. We discuss mitigations and reassess the risk (in response to deployed mitigations) and show that the risk could be reduced significantly to Very Low-Medium. We disclosed our findings to Google, which deployed dedicated mitigations.

cs.CR↗
arXiv2025

PaniCar: Securing the Perception of Advanced Driving Assistance Systems Against Emergency Vehicle Lighting

The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emergency vehicles (police cars, ambulances, and firetrucks). While previous studies have revealed that strong light sources often introduce flare artifacts in the captured image, which degrade the image quality, the impact of flare on object detection performance remains unclear. In this research, we unveil PaniCar, a digital phenomenon that causes an object detector's confidence score to fluctuate below detection thresholds when exposed to activated emergency vehicle lighting. This vulnerability poses a significant safety risk, and can cause autonomous vehicles to fail to detect objects near emergency vehicles. In addition, this vulnerability could be exploited by adversaries to compromise the security of advanced driving assistance systems (ADASs). We assess seven commercial ADASs (Tesla Model 3, "manufacturer C", HP, Pelsee, AZDOME, Imagebon, Rexing), four object detectors (YOLO, SSD, RetinaNet, Faster R-CNN), and 14 patterns of emergency vehicle lighting to understand the influence of various technical and environmental factors. We also evaluate four SOTA flare removal methods and show that their performance and latency are insufficient for real-time driving constraints. To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting. Our evaluation shows that on YOLOv3 and Faster RCNN, Caracetamol improves the models' average confidence of car detection by 0.20, the lower confidence bound by 0.33, and reduces the fluctuation range by 0.33. In addition, Caracetamol is capable of processing frames at a rate of between 30-50 FPS, enabling real-time ADAS car detection.

cs.CV↗
arXiv2025

A Privacy Enhancing Technique to Evade Detection by Street Video Cameras Without Using Adversarial Accessories

In this paper, we propose a privacy-enhancing technique leveraging an inherent property of automatic pedestrian detection algorithms, namely, that the training of deep neural network (DNN) based methods is generally performed using curated datasets and laboratory settings, while the operational areas of these methods are dynamic real-world environments. In particular, we leverage a novel side effect of this gap between the laboratory and the real world: location-based weakness in pedestrian detection. We demonstrate that the position (distance, angle, height) of a person, and ambient light level, directly impact the confidence of a pedestrian detector when detecting the person. We then demonstrate that this phenomenon is present in pedestrian detectors observing a stationary scene of pedestrian traffic, with blind spot areas of weak detection of pedestrians with low confidence. We show how privacy-concerned pedestrians can leverage these blind spots to evade detection by constructing a minimum confidence path between two points in a scene, reducing the maximum confidence and average confidence of the path by up to 0.09 and 0.13, respectively, over direct and random paths through the scene. To counter this phenomenon, and force the use of more costly and sophisticated methods to leverage this vulnerability, we propose a novel countermeasure to improve the confidence of pedestrian detectors in blind spots, raising the max/average confidence of paths generated by our technique by 0.09 and 0.05, respectively. In addition, we demonstrate that our countermeasure improves a Faster R-CNN-based pedestrian detector's TPR and average true positive confidence by 0.03 and 0.15, respectively.

cs.CV↗
arXiv2025

Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical World

The traditional learning process of patch-based adversarial attacks, conducted in the digital domain and then applied in the physical domain (e.g., via printed stickers), may suffer from reduced performance due to adversarial patches' limited transferability from the digital domain to the physical domain. Given that previous studies have considered using projectors to apply adversarial attacks, we raise the following question: can adversarial learning (i.e., patch generation) be performed entirely in the physical domain with a projector? In this work, we propose the Physical-domain Adversarial Patch Learning Augmentation (PAPLA) framework, a novel end-to-end (E2E) framework that converts adversarial learning from the digital domain to the physical domain using a projector. We evaluate PAPLA across multiple scenarios, including controlled laboratory settings and realistic outdoor environments, demonstrating its ability to ensure attack success compared to conventional digital learning-physical application (DL-PA) methods. We also analyze the impact of environmental factors, such as projection surface color, projector strength, ambient light, distance, and angle of the target object relative to the camera, on the effectiveness of projected patches. Finally, we demonstrate the feasibility of the attack against a parked car and a stop sign in a real-world outdoor environment. Our results show that under specific conditions, E2E adversarial learning in the physical domain eliminates the transferability issue and ensures evasion by object detectors. Finally, we provide insights into the challenges and opportunities of applying adversarial learning in the physical domain and explain where such an approach is more effective than using a sticker.

cs.CV↗
arXiv2024

SoK: On the Offensive Potential of AI

Our society increasingly benefits from Artificial Intelligence (AI). Unfortunately, more and more evidence shows that AI is also used for offensive purposes. Prior works have revealed various examples of use cases in which the deployment of AI can lead to violation of security and privacy objectives. No extant work, however, has been able to draw a holistic picture of the offensive potential of AI. In this SoK paper we seek to lay the ground for a systematic analysis of the heterogeneous capabilities of offensive AI. In particular we (i) account for AI risks to both humans and systems while (ii) consolidating and distilling knowledge from academic literature, expert opinions, industrial venues, as well as laypeople -- all of which being valuable sources of information on offensive AI. To enable alignment of such diverse sources of knowledge, we devise a common set of criteria reflecting essential technological factors related to offensive AI. With the help of such criteria, we systematically analyze: 95 research papers; 38 InfoSec briefings (from, e.g., BlackHat); the responses of a user study (N=549) entailing individuals with diverse backgrounds and expertise; and the opinion of 12 experts. Our contributions not only reveal concerning ways (some of which overlooked by prior work) in which AI can be offensively used today, but also represent a foothold to address this threat in the years to come.

cs.CR↗
arXiv2024

Injection Attacks Against End-to-End Encrypted Applications

We explore an emerging threat model for end-to-end (E2E) encrypted applications: an adversary sends chosen messages to a target client, thereby "injecting" adversarial content into the application state. Such state is subsequently encrypted and synchronized to an adversarially-visible storage. By observing the lengths of the resulting cloud-stored ciphertexts, the attacker backs out confidential information. We investigate this injection threat model in the context of state-of-the-art encrypted messaging applications that support E2E encrypted backups. We show proof-of-concept attacks that can recover information about E2E encrypted messages or attachments sent via WhatsApp, assuming the ability to compromise the target user's Google or Apple account (which gives access to encrypted backups). We also show weaknesses in Signal's encrypted backup design that would allow injection attacks to infer metadata including a target user's number of contacts and conversations, should the adversary somehow obtain access to the user's encrypted Signal backup. While we do not believe our results should be of immediate concern for users of these messaging applications, our results do suggest that more work is needed to build tools that enjoy strong E2E security guarantees.

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

Exploiting Leakage in Password Managers via Injection Attacks

This work explores injection attacks against password managers. In this setting, the adversary (only) controls their own application client, which they use to "inject" chosen payloads to a victim's client via, for example, sharing credentials with them. The injections are interleaved with adversarial observations of some form of protected state (such as encrypted vault exports or the network traffic received by the application servers), from which the adversary backs out confidential information. We uncover a series of general design patterns in popular password managers that lead to vulnerabilities allowing an adversary to efficiently recover passwords, URLs, usernames, and attachments. We develop general attack templates to exploit these design patterns and experimentally showcase their practical efficacy via analysis of ten distinct password manager applications. We disclosed our findings to these vendors, many of which deployed mitigations.

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

Private Hierarchical Governance for Encrypted Messaging

The increasing harms caused by hate, harassment, and other forms of abuse online have motivated major platforms to explore hierarchical governance. The idea is to allow communities to have designated members take on moderation and leadership duties; meanwhile, members can still escalate issues to the platform. But these promising approaches have only been explored in plaintext settings where community content is public to the platform. It is unclear how one can realize hierarchical governance in the huge and increasing number of online communities that utilize end-to-end encrypted (E2EE) messaging for privacy. We propose private hierarchical governance systems. These should enable similar levels of community governance as in plaintext settings, while maintaining cryptographic privacy of content and governance actions not reported to the platform. We design the first such system, taking a layered approach that adds governance logic on top of an encrypted messaging protocol; we show how an extension to the message layer security (MLS) protocol suffices for achieving a rich set of governance policies. Our approach allows developers to rapidly prototype new governance features, taking inspiration from a plaintext system called PolicyKit. We build a prototype E2EE messaging system called MlsGov that supports content-based community and platform moderation, elections of community moderators, votes to remove abusive users, and more.

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

Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an image or audio recording. When the user asks the (unmodified, benign) model about the perturbed image or audio, the perturbation steers the model to output the attacker-chosen text and/or make the subsequent dialog follow the attacker's instruction. We illustrate this attack with several proof-of-concept examples targeting LLaVa and PandaGPT.

cs.CR↗
arXiv2022

Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Models

In recent years, various watermarking methods were suggested to detect computer vision models obtained illegitimately from their owners, however they fail to demonstrate satisfactory robustness against model extraction attacks. In this paper, we present an adaptive framework to watermark a protected model, leveraging the unique behavior present in the model due to a unique random seed initialized during the model training. This watermark is used to detect extracted models, which have the same unique behavior, indicating an unauthorized usage of the protected model's intellectual property (IP). First, we show how an initial seed for random number generation as part of model training produces distinct characteristics in the model's decision boundaries, which are inherited by extracted models and present in their decision boundaries, but aren't present in non-extracted models trained on the same data-set with a different seed. Based on our findings, we suggest the Robust Adaptive Watermarking (RAW) Framework, which utilizes the unique behavior present in the protected and extracted models to generate a watermark key-set and verification model. We show that the framework is robust to (1) unseen model extraction attacks, and (2) extracted models which undergo a blurring method (e.g., weight pruning). We evaluate the framework's robustness against a naive attacker (unaware that the model is watermarked), and an informed attacker (who employs blurring strategies to remove watermarked behavior from an extracted model), and achieve outstanding (i.e., >0.9) AUC values. Finally, we show that the framework is robust to model extraction attacks with different structure and/or architecture than the protected model.

cs.CV↗
arXiv2022

EyeDAS: Securing Perception of Autonomous Cars Against the Stereoblindness Syndrome

The ability to detect whether an object is a 2D or 3D object is extremely important in autonomous driving, since a detection error can have life-threatening consequences, endangering the safety of the driver, passengers, pedestrians, and others on the road. Methods proposed to distinguish between 2 and 3D objects (e.g., liveness detection methods) are not suitable for autonomous driving, because they are object dependent or do not consider the constraints associated with autonomous driving (e.g., the need for real-time decision-making while the vehicle is moving). In this paper, we present EyeDAS, a novel few-shot learning-based method aimed at securing an object detector (OD) against the threat posed by the stereoblindness syndrome (i.e., the inability to distinguish between 2D and 3D objects). We evaluate EyeDAS's real-time performance using 2,000 objects extracted from seven YouTube video recordings of street views taken by a dash cam from the driver's seat perspective. When applying EyeDAS to seven state-of-the-art ODs as a countermeasure, EyeDAS was able to reduce the 2D misclassification rate from 71.42-100% to 2.4% with a 3D misclassification rate of 0% (TPR of 1.0). We also show that EyeDAS outperforms the baseline method and achieves an AUC of over 0.999 and a TPR of 1.0 with an FPR of 0.024.

cs.LG↗
arXiv2022

bAdvertisement: Attacking Advanced Driver-Assistance Systems Using Print Advertisements

In this paper, we present bAdvertisement, a novel attack method against advanced driver-assistance systems (ADASs). bAdvertisement is performed as a supply chain attack via a compromised computer in a printing house, by embedding a "phantom" object in a print advertisement. When the compromised print advertisement is observed by an ADAS in a passing car, an undesired reaction is triggered from the ADAS. We analyze state-of-the-art object detectors and show that they do not take color or context into account in object detection. Our validation of these findings on Mobileye 630 PRO shows that this ADAS also fails to take color or context into account. Then, we show how an attacker can take advantage of these findings to execute an attack on a commercial ADAS, by embedding a phantom road sign in a print advertisement, which causes a car equipped with Mobileye 630 PRO to trigger a false notification to slow down. Finally, we discuss multiple countermeasures which can be deployed in order to mitigate the effect of our proposed attack.

cs.CR↗