arXiv subjects

Shouling Ji

Publications and source records attributed to Shouling Ji.

At least 19 recordsLinked to original sources

arXiv2026

The Shape of Ownership: Verifying LLM Provenance through Semantic Structures

As large language models (LLMs) are increasingly redistributed, adapted, and served behind opaque APIs, model ownership can no longer be established reliably by inspecting model internals or deployment records. This creates a need for behavioral signatures that remain observable through black-box interaction. Yet most existing black-box fingerprints instantiate ownership signals through fixed query-key associations, reducing model identity to sparse memorized associations detached from ordinary behavior and limiting both robustness and stealth (e.g., fine-tuning or quantization) and stealthiness. A stronger fingerprint should instead be distributed, naturally elicited, and expressed at a higher semantic level. To this end, we introduce PROSE (Provenance through Relational Organization of Semantic Expression), replacing fixed query sets with a target semantical domain and brittle response keys with semantic structures internalized as domain-conditioned response behavior. Specifically, the fingerprint is encoded in how the model semantically organizes its in-domain conclusions, rather than in particular tokens or prescribed outputs. PROSE constructs a private bank of domain-specific semantic templates, internalizes them through mixed fine-tuning on structurally verified and clean responses, and verifies ownership by detecting the designated structures in responses to held-out natural queries. Extensive experiments across multiple model architectures, scales, and target domains show that PROSE achieves a 100% fingerprint detection rate on unmodified models with no observed false positives, preserves model utility, and retains strong detectability under downstream modifications and output transformations.

cs.CR↗

arXiv2026

A Finger on the Scale: Covert Policy Steering through Agentic Skills

Reusable agent skills extend large language model (LLM) agents with task procedures, tool-use guidance, and output constraints. Yet these skills also act as externalized behavioral policies, which create a supply-chain risk: a third-party skill may preserve the declared task and valid output interface while covertly redirecting agent decisions toward an undisclosed objective. We formalize Skill Policy Integrity, which requires a Skill-induced policy to remain aligned with its declared functionality and the user-authorized objective. We further present SkillShift, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking. It combines semantically plausible policy edits with hierarchical validation, failure-guided optimization, and strategy compression to preserve effectiveness, output validity, transferability, and inconspicuousness. We instantiate this threat in agentic commerce and software dependency use, with SkillShift achieving attacker-favored selection rates of 81.33% and 63.33% while maintaining a 100% utility-preserving rate. The frozen policies also transfer without further optimization across heterogeneous LLM backends and agent environments. Moreover, the evaluated scanners fail to detect the constructed skills, motivating behavioral auditing of reusable skills as agent policy artifacts.

cs.CR↗

arXiv2026

Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning

Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on repository poisoning largely focuses on attacker-controlled injection and disguise, but developers also shape risk through everyday invocation choices: what task to delegate, how to phrase the request, and which skills or rules to supply. We term these user-side choices Prompt-Level Configurations (PLCs) and introduce CIPR (Coding In Poisoned Repos), the first benchmark that systematically varies PLCs in poisoned real-world repositories. CIPR comprises 1,920 instances across 20 repositories, four task types, three social-media-grounded prompt styles, and three skill/rule conditions, and measures attack success rate (ASR) and agent alert rate (AR) using automated runtime and trace-based oracles. Our evaluation reveals two key insights: (1) Vulnerability is highly context-dependent, with task type creating up to a 4.5-fold difference in ASR, with test-execution task forming a silent attack surface (high ASR, low AR). (2) Prompt expression shifts risk indirectly: underspecified prompts reduce ASR by truncating execution depth; noisy prompts exhibit a directional trend toward suppressing alerts by making malicious content less conspicuous. These findings highlight that coding agent vulnerability is not a static property, but a dynamic outcome shaped by everyday user configurations.

cs.CR↗

arXiv2026

Reactive Peripheral Modeling for Faithful Firmware Rehosting

Rehosting enables tight control and introspection for firmware testing, but existing approaches largely fail to reach deeper application states and cannot drive embedded protocol stacks beyond early-stage initialization. This limitation reflects a broader weakness in current rehosting techniques: their inability to faithfully model complex peripheral semantics and dependencies. In particular, existing work typically relies on passive approximations of peripheral behavior and overlooks three key aspects: (i) the interplay among interrupts, MMIO, and DMA; (ii) implicit state transitions within peripherals; and (iii) interactions across multiple peripherals. To address this challenge, we propose Reactive Peripheral Modeling (RPM), an abstraction that models hardware peripherals as reactive and stateful systems. RPM captures peripheral behavior using event-condition-action semantics, enabling faithful representation of interrupt, MMIO, and DMA scheduling, implicit state transitions, and cross-peripheral interactions. We implement RPM in Bluezz for BLE firmware rehosting and fuzzing, and show that reactive modeling is necessary to reach deep protocol states. We evaluate Bluezz on representative BLE stacks, including NimBLE, Zephyr, and Nordic SoftDevice, a closed-source commercial stack. Across 18 targets, Bluezz achieves an average basic-block coverage more than 2.6 times that of prior state-of-the-art rehosting approaches. Unlike prior approaches, which remain largely confined to advertising and scanning logic, Bluezz reliably exercises connected BLE states and uncovers five previously unknown vulnerabilities that manifest only after connection establishment. Finally, we show that RPM generalizes beyond BLE to other embedded firmware running on different MCUs.

cs.CR↗

arXiv2026

Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe over-refusal. In this paper, we first demonstrate that LLMs can separate instruction from data intrinsically with both theoretical and empirical evidence. Inspired by this insight, we propose AEGIS (Adaptive Ensemble Guard for Injection Shielding). AEGIS extracts instruction-sensitive projectors to identify malicious instructions and leverages a Unified Multi-Layer Consensus mechanism that aggregates topologically distinct signals across the network depth. Empirical evaluations show that AEGIS achieves remarkable detection performance against both heuristic and optimization-based attacks compared to baselines, highlighting its potential to mitigate IPI. Code is available at https://github.com/xaddwell/AEGIS

cs.CR↗

arXiv2026

MazeRunner: Nonlinear Task and Clue Orchestration for LLM-driven Black-Box Automated Penetration Testing

Penetration testing is essential yet resource-intensive. Although large language models (LLMs) show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph is initially unknown and must be incrementally inferred from environmental feedback. Observations may reveal multiple attack branches, failures are often ambiguous, and critical clues may span long action horizons. Existing agents therefore tend to become trapped in depth-first exploration, misdiagnose failures, and forget prior evidence. We present MazeRunner, an autonomous penetration testing system built on a three-agent task-and-clue orchestration framework. It separates global orchestration, context-intensive execution, and failure-oriented review while persistently maintaining task states and environmental evidence. This design supports action revision, prerequisite recovery, branch switching, and long-range clue correlation. We evaluate MazeRunner on 10 recently released HTB targets, limiting each system-target run to 20 million LLM tokens and preventing target-specific solution leakage. With Claude Sonnet 4.5, MazeRunner completes 47.7% of annotated subtasks, compared with 36.2% for PentestGPT-V2 and 34.2% for Claude Code. It achieves user-level or higher access on six targets, including root access on two; each same-model baseline reaches user-level access on only two targets and never obtains root access. Execution-trace analysis further shows that MazeRunner explores more attack branches and acquires shells more efficiently.

cs.CR↗

arXiv2026

The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails

Multimodal guard models have emerged as critical safety components for screening content in vision-language systems. While adversarial research has extensively studied jailbreaking attacks that produce false negatives, the inverse threat of inducing false positives on benign inputs remains unexplored. We introduce Unsafe Induction Attacks, where adversaries distribute imperceptibly perturbed safe images that trigger guard models to reject legitimate user requests, causing a "Boy Who Cried Wolf" effect that degrades service availability and erodes trust. This reveals an availability failure mode in deployed safety filters. To realize this threat under diverse user prompts, we propose Unsafe Semantic Distillation (USD), which aligns adversarial perturbations with distributional representations of unsafe content rather than prompt-specific instances. Evaluated on four state-of-the-art guard models across realistic user simulation scenarios, USD achieves 84% attack success rates, outperforming existing methods and exposing fundamental vulnerabilities in current multimodal safety architectures.

cs.CR↗

arXiv2026

Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks

Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines such threats as decision-level hijacking. Existing attacks fail to achieve targeted cognitive manipulation without triggering prohibited content or degrading model functionality. To fill this gap, this paper reveals that Bit-Flip Attacks (BFAs) can serve as an attack vector for inducing decision-level hijacking, requiring no real-time interaction or control over the training process, and only a minimal number of weight bits need to be flipped after deployment to achieve stealthy, low-cost, and persistent cognitive manipulation. Therefore, we propose CogBias, a cognitive bias injection framework for LLMs. CogBias converts subjective preferences into optimization signals via a differentiable sentiment evaluator, uses a multi-objective loss to jointly constrain multiple dimensions, and constructs BitScout to locate critical bits, achieving targeted cognitive intervention under an ultra-sparse flip budget. Experiments on Llama-3.2-3B, Mistral-7B, and Qwen2.5-14B, as well as on the commercial recommendation and controversial factual topic scenarios, demonstrate that flipping only a small number of bits stably induces significant stance shifts on target topics, while the impact on non-target tasks and overall output distribution is limited. This work demonstrates that minute perturbations to low-level weight data suffice to undermine the high-level value alignment of LLMs.

cs.CR↗

arXiv2026

Hybrid Analysis for Secure MCP Tool Use in LLM Agents

The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safety risks, as LLM agents can be induced to perform malicious or unauthorized actions. Although prior work has proposed defenses for securing tool use in LLM agents, most methods rely on static analysis, i.e., inspecting prompts and generated outputs, which limits the defense effectiveness and robustness. To address these limitations, we propose MTGuard, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis. Extensive evaluation demonstrates that MTGuard effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.

cs.CR↗

arXiv2026

Lilith: Backdoor Generalization under Training-Inference Trigger Shift

Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persistent malicious behavior while preserving benign utility. However, existing backdoor studies largely evaluate exact trigger reuse, training-exposed trigger diversity, or variations along predefined transformation axes. They therefore leave a critical blind spot: whether a backdoor learned from one training-time trigger can generalize to an inference-time trigger family absent from victim training. We formulate this problem as backdoor generalization under training--inference trigger shift and introduce Lilith, a black-box anchor-to-family framework. Using only disjoint surrogate resources, Lilith first induces a compact target-side vulnerability with a single training anchor, then constructs a bounded inference-only family that preserves the anchor-induced representation geometry. We characterize this mechanism through anchor clearance and family reach, deriving sufficient conditions for family-wise target preservation under local regularity and bounded surrogate--victim discrepancy. Experiments across datasets, architectures, poisoning rates, and defenses show that Lilith achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap. Additional analyses show that family activation depends on representation alignment rather than the proposal mechanism, exposing a broader threat overlooked by exact-trigger evaluation.

cs.CR↗

arXiv2026

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments

x402 is an emerging payment protocol for Web APIs and autonomous AI agents. x402 extends HTTP 402 with a payment negotiation flow and delegates payment proof verification and on-chain settlement to third-party facilitators. As a result, facilitators serve as a shared payment infrastructure for many independent merchants. This centralizes trust and validation in one component, so a single flaw can affect many services. Despite rapid adoption by major vendors and economically meaningful mainnet activity, the security posture of real-world x402 deployments remains poorly characterized. We present the first systematic study of authorization correctness and execution safety in current facilitator-mediated x402 deployments in the wild, identifying eight security rules for facilitators as critical payment infrastructure. Based on our analysis of rule violations, we derive four new attack vectors, including Free Shopping, Asset Theft, Service Denial, and Gas Abuse. These attacks exploit weaknesses in the real-world facilitator and server implementations and cause severe harm, including direct financial loss to merchants, theft of facilitator-held assets, unbounded sponsor-paid gas/fees, and disruption of payment services. To assess the security of x402 deployments at scale, we propose a semi-automated black-box tool and apply it to 15 major x402 facilitators collectively used by over 60K sellers and 360K buyers. Alarmingly, we find violations in all evaluated facilitators. We responsibly disclosed our findings to the affected parties, who acknowledged the issues and adopted mitigations, including changes by Coinbase. Finally, we complement our controlled testing with an empirical measurement of over 119 million recent Base and Solana transactions, quantifying x402 adoption, facilitator centralization, and ecosystem-level risk indicators.

cs.CR↗

arXiv2026

SherAgent: Scaling Attack Investigation in the Wild via LLM-Empowered Iterative Query-Filter Backtracking

Provenance-based attack investigation enables viable automation by standardizing data and query logic; however, it is critically hindered in practice by dependency explosions and fragmented causal chains in the wild. Towards designing a robust and automated investigation tool, we collaborated with the SOC of a major Internet corporation serving billions of users. By engaging in real-world incident response, we are able to evaluate and refine their existing LLM-based investigation workflows, which processes tens of thousands of raw alerts daily, leaving thousands for manual triage, to find out the root causes of investigation failures and major challenges in their existing tools. Motivated by these findings, we propose SherAgent, an LLM-empowered automated investigation system. Operating on an iterative ``query-filter'' backtracking paradigm over provenance graphs, SherAgent leverages the semantic reasoning capabilities of LLMs to process unstructured data, such as investigation context and threat intelligence. To overcome fragmented causal chains caused by missing events, the system dynamically calibrates query conditions to broaden the search scope. Concurrently, it performs precision result filtering and strategic nodes selection for subsequent exploration, thereby mitigating dependency explosions. Extensive evaluations in the wild demonstrate that SherAgent improves the end-to-end investigation success rate by 31.1% and 63.7% compared to both legacy enterprise baselines and SOTA approaches, respectively. Furthermore, it operates with remarkable efficiency, incurring under $0.10 in API costs and requiring less than 4 minutes per investigation. Finally, our user study confirms that SherAgent provides accurate and clear insights, significantly reducing the analytical overhead for security experts.

cs.CR↗

arXiv2026

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies

Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversarial influences become permanently encoded, self-amplify across generations, and propagate through populations without sustained attacker access. We present a systematic security and privacy analysis organized around the Module-Lifecycle Attack Surface (MLAS) matrix, which decomposes the attack surface into five functional modules (Brain, Cognitive Resource, Execution, Self-Design, Collective) $\times$ five lifecycle stages (Bootstrap, Propose, Evaluate, Commit, Serve). Analysis of the resulting 25 cells reveals that 17 face critical threats for which no effective partial mitigation. We identify seven cross-cutting amplification effects that interact synergistically and cannot be addressed by securing individual modules in isolation. Comparative case studies of two open-source frameworks demonstrate that evolution-native design activates $3.5\times$ more attack surface cells and achieves a 100% attack persistence rate (40/40 payloads across all CIA+Privacy categories), while co-located security scanners block only 2.5% of attacks. Our findings establish that self-evolution converts every known attack category from session-bounded to lineage-persistent, gives rise to entirely new attack classes, and renders static defenses structurally inadequate, motivating evolution-aware security frameworks and formal verification for self-modifying systems.

cs.CR↗

arXiv2026

Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications

Large language model (LLM)-based applications rely on system prompts to encode core logic and developer-defined constraints, making these prompts important intellectual property. However, system prompts are vulnerable to prompt leaking attacks. Although prior work has shown such attacks in controlled settings, their prevalence, causes, and defenses in real-world deployments remain unclear. This paper presents a systematic study of prompt leaking in real-world LLM-based applications. We measure 1,200 applications across six major commercial platforms and find that over 80% of deployments leak system prompts under realistic adversarial queries, sometimes exposing sensitive information such as third-party API keys. We also show that existing defenses often fail to prevent leakage without degrading usability. To explain these failures, we conduct an attention-level mechanistic analysis and identify attention drift, where query-key alignment bias and softmax amplification cause LLMs to progressively ignore defensive constraints. Guided by this insight, we propose AREA, a practical defense that re-anchors the model's attention using an optimizable soft prompt. Experiments and real-world case studies show that AREA matches the leakage resistance of state-of-the-art defenses while improving average usability by over 33% and reducing optimization overhead by nearly 3x. Our responsible disclosure led two affected vendors to classify these leaks as medium-severity vulnerabilities.

cs.CR↗

arXiv2026

Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem

The prosperity of text-to-image (T2I) models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation (LoRA) plugins, which allow users to customize and share model capabilities with ease. This democratization, however, comes with a hidden but severe security risk. Malicious users could share and distribute seemingly benign LoRA plugins that contain hidden functionalities to poison the model-sharing market, like Civitai or Liblib, severely undermining the user trust that underpins this collaborative ecosystem and threatening the safety of countless downstream applications. Despite these risks, plugin poisoning in the real-world T2I ecosystem remains underexplored. This paper introduces PoisonLoRA, the first systematic study of LoRA plugin supply-chain risks that exploits the trust and characteristics within the T2I ecosystem. We identify two primary attack instances: (1) Concept Hijacking, where a hijacked LoRA could generate images to influence public opinion and spread propaganda, and (2) Task Injection, where a LoRA is injected to produce harmful content (e.g., NSFW images) only activated by a secret key. Critically, the malicious payload persists with virus-like propagation. Such propagations weaponize the very act of creative collaboration (e.g., LoRA merging) to spread its contagion, turning every remix into a new carrier. Extensive experiments validate that PoisonLoRA is both effective and stealthy. Specifically, we achieve approximately 100% attack success rates (ASR) on both Civitai and Liblib on 6 datasets across 4 scenarios, without being detected by the platforms. The poisoned LoRA demonstrates extreme robustness, with nearly 100% ASR even transferred to different base models and remixed more than 5 times.

cs.CR↗

arXiv2026

Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization

Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery localization methods, as these approaches depend on physical noise absent in synthetic data. To address this challenge, we theoretically demonstrate that the diffusion process inherently suppresses local high-frequency variance, creating a statistical energy gap that is distinguishable from the natural entropy of optical imaging. Guided by this insight, we propose FLAME, a unified framework that utilizes a LAD map to capture these intrinsic anomalies, coupled with a parameter-efficient adapter for SAM to achieve precise, pixel-level forgery localization. Furthermore, to bridge the lag between forensic benchmarks and evolving generative models, we introduce EditStream, an automated pipeline for continuous, instruction-based training data synthesis. Extensive experiments demonstrate that FLAME establishes a new state-of-the-art, significantly outperforming previous methods on AI-generated forgery datasets while effectively generalizing to unseen generative architectures. Our code is available at https://github.com/phoenixnir/FLAME.

cs.CV↗

arXiv2026

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily focus on vanilla scenarios, while plasticity interventions have emerged as indispensable built-in components of modern DRL agents. Despite their effectiveness in mitigating plasticity loss, the impact of these interventions on DRL backdoor vulnerabilities remains underexplored, and this lack of systematic investigation poses risks in practical DRL deployments. To bridge this gap, we empirically study 14,664 cases integrating representative interventions and attack scenarios. We find that only one intervention (i.e., SAM) exacerbates backdoor threats, while other interventions mitigate them. Pathological analysis identifies that the exacerbation is attributed to backdoor gradient amplification, while the mitigation stems from activation pathway disruption and representation space compression. From these findings, we derive two novel insights: (1) a conceptual framework SCC for robust backdoor injection that deconstructs the mechanistic interplay between interventions and backdoors in DRL, and (2) abnormal loss landscape sharpness as a key indicator for DRL backdoor detection.

cs.LG↗

arXiv2026

Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents

Large Language Models (LLMs) have revolutionized how information are collected, aggregated, and reasoned. However, this enables a novel and accessible vector of privacy intrusion: the automated and in-depth personal profiling; this engenders a chilling effect of "peepers everywhere". Existing research primarily unfolds from the training pipeline of LLM, emphasizing the exposure of Personally Identifiable Information (PII) through memorization, while privacy studies from a human-centric perspective remain underexplored. To fill this void, we empirically investigate privacy perception in the real world through the lens of human awareness and the practices of LLM-integrated platforms, revealing a significant dissonance: platforms fail to technically or policy-wise address public privacy concerns. To facilitate a systematic and quantifiable study of privacy risk, we propose the PrivacyIceberg, which categorizes real-world human privacy risks into three tiers: explicitly searched, contextually inferred, and deeply aggregated, based on the sophistication of LLM exploitation. We developed IcebergExplorer to audit privacy exposure, utilizing minimal PII as a search seed to reconstruct high-fidelity profiles, achieving over 90% factual accuracy within 10 minutes at a cost under $3, for real-world scenarios. Additionally, we identify six root causes contributing to such privacy disclosures and propose multi-stakeholder countermeasures for LLM vendors, individuals, and data publishers.

cs.CR↗