Searcharxiv⌕ Search

arXiv subjects

Zhen Xiang

Publications and source records attributed to Zhen Xiang.

At least 19 recordsLinked to original sources
arXiv2026

Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders

Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OBS) and hidden representation shift (IBS), measured through controlled counterfactual identity probes across gender, age, and race. Their relationship is summarized via Representation-Output Alignment (ROA), with quadrant diagnostics for identifying user-level hidden-output mismatch. Applied to six open-weight LLM families across three domains, FairGap reveals pervasive hidden-output decoupling: ROA rarely exceeds 0.22, and a non-negligible user population shows stable outputs despite substantial internal shifts, a mode that output-only audits cannot detect by design. Further, activation steering that reduces IBS by up to 8x simultaneously worsens OBS, demonstrating a fundamental tension between internal and output-level fairness that existing frameworks are unequipped to diagnose.

cs.AI↗
arXiv2026

AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent

Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities, but they also introduce significant safety and misuse risks during multi-turn interactions with external environments. Existing safety mechanisms mainly rely on external guardrails, which have a limited ability to perform fine-grained behavioral control during execution. Meanwhile, recent mechanistic interpretability methods for LLM safety are mostly confined to single-turn or jailbreak-style QA settings, limiting their ability to capture the evolving risk dynamics of multi-turn agent execution. In this paper, we investigate the safety of multi-turn coding agents from an internal perspective. We propose AgentLens (Mechanistic Subspace Intervention and Steering), a white-box defense framework that performs runtime safety detection and representation-level mitigation for coding agents. Unlike conventional agent guardrails, AgentLens detect harmful execution states from step-level hidden representations and mitigate unsafe behavior by intervening in a 10-dimensional subspace within a single layer. To support this research, we introduce the Mechanistic Agent Safety (MAS) benchmark, comprising comprehensively annotated multi-turn execution trajectories across 194 tasks using LLaMA-3.1-8B, Qwen-2.5-7B, and Gemma-2-9B. Extensive experiments show that AgentLens achieves strong safety detection performance, provides preliminary evidence for lookahead risk anticipation, and substantially reduces harmful actions of the coding agent, establishing a foundation for applying mechanistic interpretability to dynamic LLM agent safety. The code is available at: https://github.com/EddyLuo1232/AgentLens

cs.AI↗
arXiv2026

FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion

Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation. Meanwhile, emerging access-control mechanisms for LLM agents are being explored to block policy-violating requests and prevent misuse. We reveal a novel attack surface arising from agent memory operations: prohibited content that would trigger access control can be fragmented across interactions, stored in long-term memory in benign-appearing form, and later reconstructed through memory retrieval without appearing explicitly in the final user query. We propose FragFuse, the first attack that enables unprivileged users to bypass agent access control by exploiting this temporal channel introduced by long-term memory. FragFuse operates in three stages: (1) identifying rejection-responsive fragments via black-box adaptive querying with fragment masking; (2) injecting these fragments into memory using marker carrier queries; and (3) retrieving and fusing the stored fragments through a follow-up attack query. Although FragFuse can be instantiated manually for individual agents, we further develop a surrogate-based optimization scheme that tunes fusion instructions and marker designs, enabling automated attack generation without violating the attacker's threat-model assumptions. We evaluate FragFuse across four representative agent settings and task domains, covering three state-of-the-art agent access-control mechanisms. FragFuse achieves an average bypass success rate of 86.3% and an average end-to-end harmful task success rate of 41.1% across all settings, with only 4.4% average task-success degradation compared with configurations without access control. We also show that alternative defenses, including state-of-the-art prompt-injection detectors and perplexity detectors, do not effectively address this attack.

cs.CR↗
arXiv2026

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for general users but legitimate for authorized professionals, limiting helpfulness in specialized professional settings. Existing approaches either require costly realignment or rely on inference-time steering that suffers from imprecise control and added latency. To this end, we propose \textsc{Palette}, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere. Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation. \textsc{Palette} further supports modular composition: it learns domain-specific safety controls independently and composes them through parameter merging, enabling on-demand multi-domain authorization without retraining. Experiments across four safety benchmarks, multiple model variants, and both LLMs and VLMs show that \textsc{Palette} delivers precise safety control without sacrificing general utility, offering a practical path toward foundation models that adapt to diverse professional needs.

cs.AI↗
arXiv2026

Crafting Reversible SFT Behaviors in Large Language Models

Supervised fine-tuning (SFT) induces new behaviors in large language models, yet imposes no structural constraint on how these behaviors are distributed within the model. Existing behavior interpretation methods, such as circuit attribution approaches, identify sparse subnetworks correlated with SFT-induced behaviors post-hoc. However, such correlations do not imply *causal necessity*, limiting the ability to selectively control SFT-induced behaviors at inference time. We pursue an alternative by asking: can an SFT-induced behavior be deliberately compressed into a sparse, mechanistically necessary subnetwork, termed a *carrier*, while remaining controllable at inference time without weight modification? We propose (a) **Loss-Constrained Dual Descent (LCDD)**, which constructs such carriers by jointly optimizing routing masks and model weights under an explicit utility budget, and (b) **SFT-Eraser**, a soft prompt optimized via activation matching on extracted carrier channels, to reverse the SFT-induced behavior. Across safety, fixed-response, and style behaviors on multiple model families, LCDD yields sparse carriers that preserve target behaviors while enabling strong reversion when triggered by SFT-Eraser. Ablations further establish that the sparse structure is the key precondition for reversal: the same trigger optimization fails on standard SFT models, confirming that structure rather than trigger design is the operative factor. These results provide direct evidence that the learned carriers are causally necessary for the behaviors, pointing to a new direction for systematically localizing and selectively suppressing SFT-induced behaviors in deployed models.

cs.LG↗
arXiv2026

Green Shielding: A User-Centric Approach Towards Trustworthy AI

Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well addressed by existing red-teaming efforts. We propose Green Shielding, a user-centric agenda for building evidence-backed deployment guidance by characterizing how benign input variation shifts model behavior. We operationalize this agenda through the CUE criteria: benchmarks with authentic Context, reference standards and metrics that capture true Utility, and perturbations that reflect realistic variations in the Elicitation of model behavior. Guided by the PCS framework and developed with practicing physicians, we instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis (HCM-Dx), a benchmark of patient-authored queries, together with structured reference diagnosis sets and clinically grounded metrics for evaluating differential diagnosis lists. We also study perturbation regimes that capture routine input variation and show that prompt-level factors shift model behavior along clinically meaningful dimensions. Across multiple frontier LLMs, these shifts trace out Pareto-like tradeoffs. In particular, neutralization, which removes common user-level factors while preserving clinical content, increases plausibility and yields more concise, clinician-like differentials, but reduces coverage of highly likely and safety-critical conditions. Together, these results show that interaction choices can systematically shift task-relevant properties of model outputs and support user-facing guidance for safer deployment in high-stakes domains. Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.

cs.CL↗
arXiv2026

IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, INformation reTRieval through literAture reVIEW (IntraView), which aims to automate fine-grained information retrieval faithfully grounded in the provided content in response to research-driven queries, and propose IntrAgent, an LLM-based agent that addresses this challenging task. In particular, IntrAgent is designed to mimic human behaviors when reading literature for information retrieval -- identifying relevant sections and then iteratively extracting key details to refine the retrieved information. It follows a two-stage pipeline: a Section Ranking stage that prioritizes relevant literature sections through structural-knowledge-enabled reasoning, and an Iterative Reading stage that continuously extracts details and synthesizes them into concise, contextually grounded answers. To support rigorous evaluation, we introduce IntraBench, a new benchmark consisting of 315 test instances built from expert-authored questions paired with literature spanning five STEM domains. Across seven backbone LLMs, IntrAgent achieves on average 13.2% higher cross-domain accuracy than state-of-the-art RAG and research-agent baselines.

cs.IR↗
arXiv2026

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems

Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for evaluating such threats. To bridge this gap, we introduce SC-Inject-Bench, a large-scale benchmark comprising over 10,000 malicious MCP tools grounded in a taxonomy of 25+ attack types derived from MITRE ATT&CK targeting supply-chain threats. We observe that existing MCP scanners and semantic guardrails perform poorly on this benchmark. Motivated by this finding, we propose ShieldNet, a network-level guardrail framework that detects supply-chain poisoning by observing real network interactions rather than surface-level tool traces. ShieldNet integrates a man-in-the-middle (MITM) proxy and an event extractor to identify critical network behaviors, which are then processed by a lightweight classifier for attack detection. Extensive experiments show that ShieldNet achieves strong detection performance (up to 0.995 F-1 with only 0.8% false positives) while introducing little runtime overhead, substantially outperforming existing MCP scanners and LLM-based guardrails.

cs.AI↗
arXiv2026

Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain where inaccurate or misleading information can cause severe real-world harm. Despite these risks, current LLMs and safety guardrails lack rigorous alignment tailored to domain-specific food hazards. To address this gap, we introduce FoodGuardBench, the first comprehensive benchmark comprising 3,339 queries grounded in FDA guidelines, designed to evaluate the safety and robustness of LLMs. By constructing a taxonomy of food safety principles and employing representative jailbreak attacks (e.g., AutoDAN and PAP), we systematically evaluate existing LLMs and guardrails. Our evaluation results reveal three critical vulnerabilities: First, current LLMs exhibit sparse safety alignment in the food-related domain, easily succumbing to a few canonical jailbreak strategies. Second, when compromised, LLMs frequently generate actionable yet harmful instructions, inadvertently empowering malicious actors and posing tangible risks. Third, existing LLM-based guardrails systematically overlook these domain-specific threats, failing to detect a substantial volume of malicious inputs. To mitigate these vulnerabilities, we introduce FoodGuard-4B, a specialized guardrail model fine-tuned on our datasets to safeguard LLMs within food-related domains.

cs.CR↗
arXiv2026

RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm

Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g., private databases, global corpora, and APIs) remains a significant challenge. Existing approaches typically employ an LLM-as-a-Router to dispatch decomposed sub-queries to specific sources in a predictive manner. However, this "LLM-as-a-Router" strategy relies heavily on the semantic meaning of different data sources, often leading to routing errors when source boundaries are ambiguous. In this work, we introduce RealRoute System, a framework that shifts the paradigm from predictive routing to a robust Retrieve-then-Verify mechanism. RealRoute ensures \textit{evidence completeness through parallel, source-agnostic retrieval, followed by a dynamic verifier that cross-checks the results and synthesizes a factually grounded answer}. Our demonstration allows users to visualize the real-time "re-routing" process and inspect the verification chain across multiple knowledge silos. Experiments show that RealRoute significantly outperforms predictive baselines in the multi-hop Rag reasoning task. The RealRoute system is released as an open-source toolkit with a user-friendly web interface. The code is available at the URL: https://github.com/Joseph1951210/RealRoute.

cs.IR↗
arXiv2026

Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment

Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduces safety risks. Existing defenses either embed safety recovery into fine-tuning or rely on fine-tuning-derived priors for post-hoc correction, leaving safety recovery tightly coupled with training and incurring high computational overhead and a complex workflow. To address these challenges, we propose \texttt{Q-realign}, a post-hoc defense method based on post-training quantization, guided by an analysis of representational structure. By reframing quantization as a dual-objective procedure for compression and safety, \texttt{Q-realign} decouples safety alignment from fine-tuning and naturally piggybacks into modern deployment pipelines. Experiments across multiple models and datasets demonstrate that our method substantially reduces unsafe behaviors while preserving task performance, with significant reductions in memory usage and GPU hours. Notably, our approach can recover the safety alignment of a fine-tuned 7B LLM on a single RTX 4090 within 40 minutes. Overall, our work provides a practical, turnkey solution for safety-aware deployment.

cs.LG↗
arXiv2025

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a crucial role in instructing LLMs to generate coherent and context-aware responses. We demonstrate that special tokens can be exploited to construct four attack primitives, with which malicious users can reliably bypass the internal safety alignment of online LLM services and circumvent state-of-the-art (SOTA) external content moderation systems simultaneously. Moreover, we found that addressing this threat is challenging, as aggressive defense mechanisms-such as input sanitization by removing special tokens entirely, as suggested in academia-are less effective than anticipated. This is because such defense can be evaded when the special tokens are replaced by regular ones with high semantic similarity within the tokenizer's embedding space. We systemically evaluated our method, named MetaBreak, on both lab environment and commercial LLM platforms. Our approach achieves jailbreak rates comparable to SOTA prompt-engineering-based solutions when no content moderation is deployed. However, when there is content moderation, MetaBreak outperforms SOTA solutions PAP and GPTFuzzer by 11.6% and 34.8%, respectively. Finally, since MetaBreak employs a fundamentally different strategy from prompt engineering, the two approaches can work synergistically. Notably, empowering MetaBreak on PAP and GPTFuzzer boosts jailbreak rates by 24.3% and 20.2%, respectively.

cs.CR↗
arXiv2025

Your Harness is Not Secure: Benchmarking Real-world Threat of Command Line Interface Agent

Command-line interface (CLI) agents powered by large language models (LLMs) can interpret natural-language requests, plan multi-step tasks, execute shell commands, and modify files and system state. As these agents are increasingly used for operating-system (OS) workflows, it is important to evaluate whether they can be misused to carry out security-relevant operations. Existing benchmarks often lack an attacker-knowledge model grounded in tactics, techniques, and procedures (TTPs), provide limited coverage of end-to-end kill chains, rely on simplified single-host environments, or use LLM-as-a-judge for success evaluation. We introduce AdvCLI, an MITRE ATT&CK-aligned benchmark for evaluating OS-level misuse risks of CLI agents in a controlled multi-host sandbox. AdvCLI contains 140 tasks: 40 direct malicious requests, 74 TTP-based tasks, and 26 end-to-end kill chains. Each task is paired with deterministic hard-coded verification protocols that check whether the requested OS-level effect is realized. We evaluate seven CLI agents and products built on nine foundation models, including ReAct, OpenClaw, OpenAI Agent SDK, Claude Code, Gemini CLI, Cursor CLI, and Cursor IDE. Results show that current CLI agents frequently proceed beyond refusal and can complete a non-negligible fraction of malicious OS-level tasks, especially when requests include TTP-style attacker knowledge. AdvCLI provides a reproducible testbed for evaluating these risks and for developing stronger safety mechanisms for tool-using CLI agents in the future.

cs.CR↗
arXiv2025

Adaptive Content Restriction for Large Language Models via Suffix Optimization

Large Language Models (LLMs) have demonstrated significant success across diverse applications. However, enforcing content restrictions remains a significant challenge due to their expansive output space. One aspect of content restriction is preventing LLMs from generating harmful content via model alignment approaches such as supervised fine-tuning (SFT). Yet, the need for content restriction may vary significantly across user groups, change rapidly over time, and not always align with general definitions of harmfulness. Applying SFT to each of these specific use cases is impractical due to the high computational, data, and storage demands. Motivated by this need, we propose a new task called \textit{Adaptive Content Restriction} (AdaCoRe), which focuses on lightweight strategies -- methods without model fine-tuning -- to prevent deployed LLMs from generating restricted terms for specific use cases. We propose the first method for AdaCoRe, named \textit{Suffix Optimization (SOP)}, which appends a short, optimized suffix to any prompt to a) prevent a target LLM from generating a set of restricted terms, while b) preserving the output quality. To evaluate AdaCoRe approaches, including our SOP, we create a new \textit{Content Restriction Benchmark} (CoReBench), which contains 400 prompts for 80 restricted terms across 8 carefully selected categories. We demonstrate the effectiveness of SOP on CoReBench, which outperforms the system-level baselines such as system suffix by 15\%, 17\%, 10\%, 9\%, and 6\% on average restriction rates for Gemma2-2B, Mistral-7B, Vicuna-7B, Llama3-8B, and Llama3.1-8B, respectively. We also demonstrate that SOP is effective on POE, an online platform hosting various commercial LLMs, highlighting its practicality in real-world scenarios.

cs.CL↗
arXiv2025

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges

Due to the remarkable capabilities and growing impact of large language models (LLMs), they have been deeply integrated into many aspects of society. Thus, ensuring their alignment with human values and intentions has emerged as a critical challenge. This survey provides a comprehensive overview of practical alignment techniques, training protocols, and empirical findings in LLM alignment. We analyze the development of alignment methods across diverse paradigms, characterizing the fundamental trade-offs between core alignment objectives. Our analysis shows that while supervised fine-tuning enables basic instruction-following, preference-based methods offer more flexibility for aligning with nuanced human intent. We discuss state-of-the-art techniques, including Direct Preference Optimization (DPO), Constitutional AI, brain-inspired methods, and alignment uncertainty quantification (AUQ), highlighting their approaches to balancing quality and efficiency. We review existing evaluation frameworks and benchmarking datasets, emphasizing limitations such as reward misspecification, distributional robustness, and scalable oversight. We summarize strategies adopted by leading AI labs to illustrate the current state of practice. We conclude by outlining open problems in oversight, value pluralism, robustness, and continuous alignment. This survey aims to inform both researchers and practitioners navigating the evolving landscape of LLM alignment.

cs.AI↗
arXiv2025

RadFabric: Agentic AI System with Reasoning Capability for Radiology

Chest X ray (CXR) imaging remains a critical diagnostic tool for thoracic conditions, but current automated systems face limitations in pathology coverage, diagnostic accuracy, and integration of visual and textual reasoning. To address these gaps, we propose RadFabric, a multi agent, multimodal reasoning framework that unifies visual and textual analysis for comprehensive CXR interpretation. RadFabric is built on the Model Context Protocol (MCP), enabling modularity, interoperability, and scalability for seamless integration of new diagnostic agents. The system employs specialized CXR agents for pathology detection, an Anatomical Interpretation Agent to map visual findings to precise anatomical structures, and a Reasoning Agent powered by large multimodal reasoning models to synthesize visual, anatomical, and clinical data into transparent and evidence based diagnoses. RadFabric achieves significant performance improvements, with near-perfect detection of challenging pathologies like fractures (1.000 accuracy) and superior overall diagnostic accuracy (0.799) compared to traditional systems (0.229 to 0.527). By integrating cross modal feature alignment and preference-driven reasoning, RadFabric advances AI-driven radiology toward transparent, anatomically precise, and clinically actionable CXR analysis.

cs.CV↗
arXiv2025

Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS

TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working collaboratively, are increasingly deployed in high-stakes applications but face novel security threats due to their complex structures. While single-agent vulnerabilities are well-studied, LLM-MAS introduces unique attack surfaces through inter-agent communication, trust relationships, and tool integration that remain significantly underexplored. We present a systematic framework for vulnerability analysis of LLM-MAS that unifies diverse research. For each type of vulnerability, we define formal threat models grounded in practical attacker capabilities and illustrate them using real-world LLM-MAS applications. This formulation enables rigorous quantification of vulnerability across different architectures and provides a foundation for designing meaningful evaluation benchmarks. We also identify critical open challenges: (1) developing benchmarks specifically tailored to LLM-MAS vulnerability assessment, (2) considering new potential attacks specific to multi-agent architectures, and (3) implementing trust management systems that can enforce security in LLM-MAS. This research provides essential groundwork for future efforts to enhance LLM-MAS trustworthiness.

cs.CR↗
arXiv2025

CDR-Agent: Intelligent Selection and Execution of Clinical Decision Rules Using Large Language Model Agents

Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3\% (synthetic) and 8.7\% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection. Moreover, CDR-Agent significantly reduces computational overhead. Using these datasets, we demonstrated that CDR-Agent not only selects relevant CDRs efficiently, but makes cautious yet effective imaging decisions by minimizing unnecessary interventions while successfully identifying most positively diagnosed cases, outperforming traditional LLM prompting approaches. Code for our work can be found at: https://github.com/zhenxianglance/medagent-cdr-agent

cs.LG↗