Search arXiv⌕ Search

arXiv subjects

Chong Xiang

Publications and source records attributed to Chong Xiang.

At least 19 recordsLinked to original sources

MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark

Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility counterparts, only offering limited task and environment coverage and relying on narrow, static attack scenarios. In this paper, we propose meta-benchmarking for IPI: transforming existing utility benchmarks into end-to-end IPI evaluation suites that reuse their realistic tasks, environments, and infrastructure. We present MetaPI, an extensible toolkit that automatically identifies plausible injection points, generates realistic attack objectives, optimizes adaptive payloads, and validates attacks in the real environment. Its modular interfaces support heterogeneous environments, agents, defenses, and attack algorithms, allowing new components to be integrated without redesigning the evaluation pipeline. We apply MetaPI to AppWorld, VitaBench, and Terminal-Bench and evaluate representative agents and defenses across multiple backbone LLMs. Our results show that no evaluated defense simultaneously achieves strong utility and strong security in realistic, adaptive agentic IPI settings. MetaPI thus enables scalable and consistent security evaluation across diverse and evolving agent ecosystems

cs.CR↗

Improving Instruction Hierarchy by Learning from Goal-Goal Conflicts

The recent incident in which OpenAI agents autonomously compromised Hugging Face's infrastructure illustrates the importance of instruction hierarchy (IH): an LLM should follow lower-priority instructions, such as user requests, only when they do not conflict with higher-priority instructions, such as system policies. IH can be effectively improved by fine-tuning LLMs on simulated examples of instruction conflicts, whose diversity is key to teaching LLMs to properly handle conflicts at test time. However, our decomposition of a task into goals and constraints reveals a conflict type -- goal-goal conflicts -- that is absent from existing IH training sets from OpenAI and NVIDIA. We show the importance of this conflict type: fine-tuning Qwen3.5-9B and Gemma4-12B-it on examples of this conflict type significantly improves IH on a wide range of real-world tasks unseen in training; adding these examples to existing IH training sets for fine-tuning also gives better IH adherence. The IH gains come with trivial mean utility changes on no-conflict tasks across eight benchmarks. Our work advocates including this new conflict type in IH training, even if these examples do not reflect typical LLM use.

cs.AI↗

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Large language model (LLM) agents can translate natural-language requests into real-world actions, creating safety risks from both indirect prompt injections and directly harmful requests. Existing system-level safety harnesses are typically designed by experts and applied across heterogeneous models and domains, despite substantial differences in model behavior, utility tolerance, and domain-specific safety requirements. We present EvoSafeHarness, a framework for automatically synthesizing deployment-specific safety harnesses for frozen LLM agents. Given a target model and domain specification, EvoSafeHarness jointly evolves a natural-language policy and executable enforcement logic using behavioral feedback from the target model. Each candidate is additionally evaluated through fresh-context adversarial review to filter rules that depend on benchmark artifacts. Across four agent benchmark families, EvoSafeHarness achieves a stronger safety-utility frontier than fixed expert-designed defenses. On DecodingTrust-Agent, evaluated across fifteen model-domain deployments, it reduces attack success rate from 50.9% to 12.6% for direct attacks and from 40.4% to 7.4% for indirect attacks, with a 3.3-point utility cost. On AgentDojo, it achieves 82.8% utility with 0.0% attack success rate, twice the utility of CaMeL at the same zero-attack-success operating point, while the same harness transfers unchanged to unseen AgentDyn suites. It also achieves the best score on Agent-SafetyBench for every evaluated victim model and maintains an attack success rate below 18% against an adaptive PAIR-style attacker with sixteen attempts per task. Analysis of the synthesized harnesses shows that domain semantics determine which safety relations and trajectory state must be tracked, while model and runtime behavior determine how and where those relations should be enforced.

cs.CR↗

Certifiably Robust RAG against Retrieval Corruption

Retrieval-augmented generation (RAG) is susceptible to retrieval corruption attacks, where malicious passages injected into retrieval results can lead to inaccurate model responses. We propose RobustRAG, the first defense framework with certifiable robustness against retrieval corruption attacks. The key insight of RobustRAG is an isolate-then-aggregate strategy: we isolate passages into disjoint groups, generate LLM responses based on the concatenated passages from each isolated group, and then securely aggregate these responses for a robust output. To instantiate RobustRAG, we design keyword-based and decoding-based algorithms for securely aggregating unstructured text responses. Notably, RobustRAG achieves certifiable robustness: for certain queries in our evaluation datasets, we can formally certify non-trivial lower bounds on response quality -- even against an adaptive attacker with full knowledge of the defense and the ability to arbitrarily inject a bounded number of malicious passages. We evaluate RobustRAG on the tasks of open-domain question-answering and free-form long text generation and demonstrate its effectiveness across three datasets and three LLMs.

cs.LG↗

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our vision for system-level defenses against indirect prompt injection attacks. We articulate three positions: (1) dynamic replanning and security policy updates are often necessary for dynamic tasks and realistic environments; (2) certain context-dependent security decisions would still require LLMs (or other learned models), but should only be made within system designs that strictly constrain what the model can observe and decide; (3) in inherently ambiguous cases, personalization and human interaction should be treated as core design considerations. In addition to our main positions, we discuss limitations of existing benchmarks that can create a false sense of utility and security. We also highlight the value of system-level defenses, which serve as the skeleton of agentic systems by structuring and controlling agent behaviors, integrating rule-based and model-based security checks, and enabling more targeted research on model robustness and human interaction.

cs.CR↗

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typically classify any input with instruction as malicious, leading to misclassification of benign inputs containing instructions that align with the intended task. In this work, we account for the instruction hierarchy and distinguish among three categories: inputs with misaligned instructions, inputs with aligned instructions, and non-instruction inputs. We introduce AlignSentinel, a three-class classifier that leverages features derived from LLM's attention maps to categorize inputs accordingly. To support evaluation, we construct the first systematic benchmark containing inputs from all three categories. Experiments on both our benchmark and existing ones--where inputs with aligned instructions are largely absent--show that AlignSentinel accurately detects inputs with misaligned instructions and substantially outperforms baselines.

cs.CR↗

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search

Retrieval-Augmented Generation (RAG) enhances Large Language Models by grounding their outputs in external documents. These systems, however, remain vulnerable to attacks on the retrieval corpus, such as prompt injection. RAG-based search systems (e.g., Google's Search AI Overview) present an interesting setting for studying and protecting against such threats, as defense algorithms can benefit from built-in reliability signals -- like document ranking -- and represent a non-LLM challenge for the adversary due to decades of work to thwart SEO. Motivated by, but not limited to, this scenario, this work introduces ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents. Our first contribution adopts a graph-theoretic perspective to identify a "consistent majority" among retrieved documents to filter out malicious ones. We introduce a novel algorithm based on finding a Maximum Independent Set (MIS) on a document graph where edges encode contradiction. Our MIS variant explicitly prioritizes higher-reliability documents and provides provable robustness guarantees against bounded adversarial corruption under natural assumptions. Recognizing the computational cost of exact MIS for large retrieval sets, our second contribution is a scalable weighted sample and aggregate framework. It explicitly utilizes reliability information, preserving some robustness guarantees while efficiently handling many documents. We present empirical results showing ReliabilityRAG provides superior robustness against adversarial attacks compared to prior methods, maintains high benign accuracy, and excels in long-form generation tasks where prior robustness-focused methods struggled. Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.

cs.CR↗

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK presents a comprehensive overview of the PI landscape, covering attacks, defenses, and their evaluation practices. Through a systematic literature review and quantitative analysis, we establish taxonomies that categorize PI attacks by payload generation strategies (heuristic vs. optimization) and defenses by intervention stages (text, model, and execution levels). Our analysis reveals a key limitation shared by many existing defenses and benchmarks: they largely overlook context-dependent tasks, in which agents are authorized to rely on runtime environmental observations to determine actions. To address this gap, we introduce AgentPI, a new benchmark designed to systematically evaluate agent behavior under context-dependent interaction settings. Using AgentPI, we empirically evaluate representative defenses and show that no single approach can simultaneously achieve high trustworthiness, high utility, and low latency. Moreover, we show that many defenses appear effective under existing benchmarks by suppressing contextual inputs, yet fail to generalize to realistic agent settings where context-dependent reasoning is essential. This SoK distills key takeaways and open research problems, offering structured guidance for future research and practical deployment of secure LLM agents.

cs.CR↗

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high computational cost of reasoning. We first formalize inference cost for LRMs and define PI-DoS, then prove that any practical PI-DoS attack should satisfy three properties: (1) a high amplification ratio, where each query induces a disproportionately long reasoning trace relative to its own length; (ii) stealthiness, in which prompts and responses remain on the natural language manifold and evade distribution shift detectors; and (iii) optimizability, in which the attack supports efficient optimization without being slowed by its own success. Under this framework, we present ReasoningBomb, a reinforcement-learning-based PI-DoS framework that is guided by a constant-time surrogate reward and trains a large reasoning-model attacker to generate short natural prompts that drive victim LRMs into pathologically long and often effectively non-terminating reasoning. Across seven open-source models (including LLMs and LRMs) and three commercial LRMs, ReasoningBomb induces 18,759 completion tokens on average and 19,263 reasoning tokens on average across reasoning models. It outperforms the the runner-up baseline by 35% in completion tokens and 38% in reasoning tokens, while inducing 6-7x more tokens than benign queries and achieving 286.7x input-to-output amplification ratio averaged across all samples. Additionally, our method achieves 99.8% bypass rate on input-based detection, 98.7% on output-based detection, and 98.4% against strict dual-stage joint detection.

cs.CR↗

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense framework based on instruction-following intent analysis. The key insight of IntentGuard is that the decisive factor in IPIAs is not the presence of malicious text, but whether the LLM intends to follow instructions from untrusted data. Building on this insight, IntentGuard leverages an instruction-following intent analyzer (IIA) to identify which parts of the input prompt the model recognizes as actionable instructions, and then flag or neutralize any overlaps with untrusted data segments. To instantiate the framework, we develop an IIA that uses three "thinking intervention" strategies to elicit a structured list of intended instructions from reasoning-enabled LLMs. These techniques include start-of-thinking prefilling, end-of-thinking refinement, and adversarial in-context demonstration. We evaluate IntentGuard on two agentic benchmarks (AgentDojo and Mind2Web) using two reasoning-enabled LLMs (Qwen-3-32B and gpt-oss-20B). Results demonstrate that IntentGuard achieves (1) no utility degradation in all but one setting and (2) strong robustness against adaptive prompt injection attacks (e.g., reducing attack success rates from 100% to 8.5% in a Mind2Web scenario).

cs.CR↗

Does More Inference-Time Compute Really Help Robustness?

Recently, Zaremba et al. demonstrated that increasing inference-time computation improves robustness in large proprietary reasoning LLMs. In this paper, we first show that smaller-scale, open-source models (e.g., DeepSeek R1, Qwen3, Phi-reasoning) can also benefit from inference-time scaling using a simple budget forcing strategy. More importantly, we reveal and critically examine an implicit assumption in prior work: intermediate reasoning steps are hidden from adversaries. By relaxing this assumption, we identify an important security risk, intuitively motivated and empirically verified as an inverse scaling law: if intermediate reasoning steps become explicitly accessible, increased inference-time computation consistently reduces model robustness. Finally, we discuss practical scenarios where models with hidden reasoning chains are still vulnerable to attacks, such as models with tool-integrated reasoning and advanced reasoning extraction attacks. Our findings collectively demonstrate that the robustness benefits of inference-time scaling depend heavily on the adversarial setting and deployment context. We urge practitioners to carefully weigh these subtle trade-offs before applying inference-time scaling in security-sensitive, real-world applications.

cs.AI↗

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of these attacks calls for certifiable defenses, which feature provable guarantees on robustness. While certifiable defenses have been successfully applied to single-label classification, limited work has been done for multi-label classification. In this work, we present PatchDEMUX, a certifiably robust framework for multi-label classifiers against adversarial patches. Our approach is a generalizable method which can extend any existing certifiable defense for single-label classification; this is done by considering the multi-label classification task as a series of isolated binary classification problems to provably guarantee robustness. Furthermore, in the scenario where an attacker is limited to a single patch we propose an additional certification procedure that can provide tighter robustness bounds. Using the current state-of-the-art (SOTA) single-label certifiable defense PatchCleanser as a backbone, we find that PatchDEMUX can achieve non-trivial robustness on the MS-COCO and PASCAL VOC datasets while maintaining high clean performance

cs.CR↗

Effectively Controlling Reasoning Models through Thinking Intervention

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging generation framework offers a unique opportunity for more fine-grained control over model behavior. We propose Thinking Intervention, a novel paradigm designed to explicitly guide the internal reasoning processes of LLMs by strategically inserting or revising specific thinking tokens. We find that the Thinking Intervention paradigm enhances the capabilities of reasoning models across a wide range of tasks, including instruction following on IFEval and Overthinking, instruction hierarchy on SEP, and safety alignment on XSTest and SorryBench. Our results demonstrate that Thinking Intervention significantly outperforms baseline prompting approaches, achieving up to 6.7% accuracy gains in instruction-following scenarios, 15.4% improvements in reasoning about instruction hierarchies, and a 40.0% increase in refusal rates for unsafe prompts using open-source DeepSeek R1 models. Overall, our work opens a promising new research avenue for controlling reasoning LLMs.

cs.LG↗

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy

Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabilities is the lack of an instruction hierarchy. Modern LLM architectures treat all inputs equally, failing to distinguish between and prioritize various types of instructions, such as system messages, user prompts, and data. As a result, lower-priority user prompts may override more critical system instructions, including safety protocols. Existing approaches to achieving instruction hierarchy, such as delimiters and instruction-based training, do not address this issue at the architectural level. We introduce the Instructional Segment Embedding (ISE) technique, inspired by BERT, to modern large language models, which embeds instruction priority information directly into the model. This approach enables models to explicitly differentiate and prioritize various instruction types, significantly improving safety against malicious prompts that attempt to override priority rules. Our experiments on the Structured Query and Instruction Hierarchy benchmarks demonstrate an average robust accuracy increase of up to 15.75% and 18.68%, respectively. Furthermore, we observe an improvement in instruction-following capability of up to 4.1% evaluated on AlpacaEval. Overall, our approach offers a promising direction for enhancing the safety and effectiveness of LLM architectures.

cs.LG↗

Position: Towards Resilience Against Adversarial Examples

Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as $\ell_2$ or $\ell_{\infty}$-bounded attacks. However, the space of possible perturbations is much larger than considered by many existing defenses and is difficult to mathematically model, so the attacker can easily bypass the defense by using a type of attack that is not covered by the defense. In this position paper, we argue that in addition to robustness, we should also aim to develop defense algorithms that are adversarially resilient -- defense algorithms should specify a means to quickly adapt the defended model to be robust against new attacks. We provide a definition of adversarial resilience and outline considerations of designing an adversarially resilient defense. We then introduce a subproblem of adversarial resilience which we call continual adaptive robustness, in which the defender gains knowledge of the formulation of possible perturbation spaces over time and can then update their model based on this information. Additionally, we demonstrate the connection between continual adaptive robustness and previously studied problems of multiattack robustness and unforeseen attack robustness and outline open directions within these fields which can contribute to improving continual adaptive robustness and adversarial resilience.

cs.LG↗

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses

State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time computation compared to undefended models -- the research community has witnessed an intense three-way trade-off between certifiable robustness, model utility, and computation efficiency. In this paper, we propose a defense framework named PatchCURE to approach this trade-off problem. PatchCURE provides sufficient "knobs" for tuning defense performance and allows us to build a family of defenses: the most robust PatchCURE instance can match the performance of any existing state-of-the-art defense (without efficiency considerations); the most efficient PatchCURE instance has similar inference efficiency as undefended models. Notably, PatchCURE achieves state-of-the-art robustness and utility performance across all different efficiency levels, e.g., 16-23% absolute clean accuracy and certified robust accuracy advantages over prior defenses when requiring computation efficiency to be close to undefended models. The family of PatchCURE defenses enables us to flexibly choose appropriate defenses to satisfy given computation and/or utility constraints in practice.

cs.CV↗

MultiRobustBench: Benchmarking Robustness Against Multiple Attacks

The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded Lp-norm) attack, but for a practical setting, machine learning (ML) models should be robust to a wide variety of attacks. In this paper, we present the first unified framework for considering multiple attacks against ML models. Our framework is able to model different levels of learner's knowledge about the test-time adversary, allowing us to model robustness against unforeseen attacks and robustness against unions of attacks. Using our framework, we present the first leaderboard, MultiRobustBench, for benchmarking multiattack evaluation which captures performance across attack types and attack strengths. We evaluate the performance of 16 defended models for robustness against a set of 9 different attack types, including Lp-based threat models, spatial transformations, and color changes, at 20 different attack strengths (180 attacks total). Additionally, we analyze the state of current defenses against multiple attacks. Our analysis shows that while existing defenses have made progress in terms of average robustness across the set of attacks used, robustness against the worst-case attack is still a big open problem as all existing models perform worse than random guessing.

cs.LG↗

ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking

Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single physically-realizable adversarial patch to make the object detector miss the detection of victim objects and undermine the functionality of object detection applications. In this paper, we propose ObjectSeeker for certifiably robust object detection against patch hiding attacks. The key insight in ObjectSeeker is patch-agnostic masking: we aim to mask out the entire adversarial patch without knowing the shape, size, and location of the patch. This masking operation neutralizes the adversarial effect and allows any vanilla object detector to safely detect objects on the masked images. Remarkably, we can evaluate ObjectSeeker's robustness in a certifiable manner: we develop a certification procedure to formally determine if ObjectSeeker can detect certain objects against any white-box adaptive attack within the threat model, achieving certifiable robustness. Our experiments demonstrate a significant (~10%-40% absolute and ~2-6x relative) improvement in certifiable robustness over the prior work, as well as high clean performance (~1% drop compared with undefended models).

cs.CV↗