arXiv subjects

Shouling Ji

Publications and source records attributed to Shouling Ji.

At least 55 records · Page 3Linked to original sources

arXiv2026

Unveiling the Security Risks of Federated Learning in the Wild: From Research to Practice

Federated learning (FL) has attracted substantial attention in both academia and industry, yet its practical security posture remains poorly understood. In particular, a large body of poisoning research is evaluated under idealized assumptions about attacker participation, client homogeneity, and success metrics, which can substantially distort how security risks are perceived in deployed FL systems. This paper revisits FL security from a measurement perspective. We systematize three major sources of mismatch between research and practice: unrealistic poisoning threat models, the omission of hybrid heterogeneity, and incomplete metrics that overemphasize peak attack success while ignoring stability and utility cost. To study these gaps, we build TFLlib, a uniform evaluation framework that supports image, text, and tabular FL tasks and re-implements representative poisoning attacks under practical settings. Our empirical study shows that idealized evaluation often overstates security risk. Under practical settings, attack performance becomes markedly more dataset-dependent and unstable, and several attacks that appear consistently strong in idealized FL lose effectiveness or incur clear benign-task degradation once practical constraints are enforced. These findings further show that final-round attack success alone is insufficient for security assessment; practical measurement must jointly consider effectiveness, temporal stability, and collateral utility loss. Overall, this work argues that many conclusions in the FL poisoning literature are not directly transferable to real deployments. By tightening the threat model and using measurement protocols aligned with practice, we provide a more realistic view of the security risks faced by contemporary FL systems and distill concrete guidance for future FL security evaluation. Our code is available at https://github.com/xaddwell/TFLlib

cs.CR↗

arXiv2026

Weaver: Fuzzing JavaScript Engines at the JavaScript-WebAssembly Boundary

The security of modern JavaScript (JS) engines is critical since they provide the primary defense mechanism for executing untrusted code on the web. The recent integration of WebAssembly (Wasm) has transformed these engines into complex polyglot environments, creating a novel attack surface at the JS-Wasm interaction boundary due to the distinct type systems and memory models of two languages. This boundary remains largely underexplored, as previous works mainly focus on testing JS and Wasm as two isolated entities rather than investigating the security implications of their cross-language interactions. This paper proposes Weaver, an effective greybox fuzzing framework specifically tailored to uncover vulnerabilities at the JS-Wasm boundary. To comply with the language constraints, Weaver uses a type-aware generation strategy, meticulously maintaining the dual-type representation for every generated variables. This allows fuzzer to validly utilize variables across the language boundary. Besides, Weaver leverages the UCB-1 algorithm to intelligently schedule mutators and generators to maximize the discovery of new code paths. We have implemented and evaluated Weaver on three JS engines. The results indicate that Weaver achieves superior code coverage compared to state-of-the-art fuzzers. Moreover, Weaver has uncovered two new bugs in the latest versions of these engines, one of which is considered high severity and set to highest priority, demonstrating the practicality of Weaver.

cs.CR↗

arXiv2026

Beyond Static Pattern Matching? Rethinking Automatic Cryptographic API Misuse Detection in the Era of LLMs

While the automated detection of cryptographic API misuses has progressed significantly, its precision diminishes for intricate targets due to the reliance on manually defined patterns. Large Language Models (LLMs) offer a promising context-aware understanding to address this shortcoming, yet the stochastic nature and the hallucination issue pose challenges to their applications in precise security analysis. This paper presents the first systematic study to explore LLMs' application in cryptographic API misuse detection. Our findings are noteworthy: The instability of directly applying LLMs results in over half of the initial reports being false positives. Despite this, the reliability of LLM-based detection could be significantly enhanced by aligning detection scopes with realistic scenarios and employing a novel code and analysis validation technique, achieving a nearly 90% detection recall. This improvement substantially surpasses traditional methods and leads to the discovery of previously unknown vulnerabilities in established benchmarks. Nevertheless, we identify recurring failure patterns that illustrate current LLMs' blind spots. Leveraging these findings, we deploy an LLM-based detection system and uncover 63 new vulnerabilities (47 confirmed, 7 already fixed) in open-source Java and Python repositories, including prominent projects like Apache.

cs.CR↗

arXiv2026

OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences

While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or situational violations. We propose shifting the safety frontier toward consequence-driven safety, a paradigm essential for the robust deployment of autonomous and embodied agents. To formalize this shift, we introduce OOD-MMSafe, a benchmark comprising 455 curated query-image pairs designed to evaluate a model's ability to identify latent hazards within context-dependent causal chains. Our analysis reveals a pervasive causal blindness among frontier models, with the highest 67.5% failure rate in high-capacity closed-source models, and identifies a preference ceiling where static alignment yields format-centric failures rather than improved safety reasoning as model capacity grows. To address these bottlenecks, we develop the Consequence-Aware Safety Policy Optimization (CASPO) framework, which integrates the model's intrinsic reasoning as a dynamic reference for token-level self-distillation rewards. Experimental results demonstrate that CASPO significantly enhances consequence projection, reducing the failure ratio of risk identification to 7.3% for Qwen2.5-VL-7B and 5.7% for Qwen3-VL-4B while maintaining overall effectiveness.

cs.AI↗

arXiv2026

PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to jailbreak attacks, where carefully crafted inputs can bypass safety mechanisms and elicit harmful responses. In this work, we investigate the security vulnerabilities of MLLMs in text-vision scenarios and propose a novel black-box jailbreak framework, named PolyJailbreak. We first identify a phenomenon, termed multimodal safety asymmetry, where visual alignment introduces uneven safety constraints across modalities and weakens overall robustness. We analyze attention dynamics and latent representations in MLLMs, revealing that visual inputs can disrupt cross-modal information flow and reduce the model's ability to separate benign and malicious intents. Motivated by these findings, we propose PolyJailbreak, which organizes the discovered vulnerabilities into a structured library of reusable Atomic Strategy Primitives to enable step-wise transformations from harmful intents to effective jailbreak inputs. Guided by these primitives, a reinforcement learning-based multi-agent optimization process automatically adapts attacks to the target model without access to internal parameters. Extensive experiments on a wide range of MLLMs demonstrate that PolyJailbreak consistently outperforms state-of-the-art jailbreak baselines, with an average improvement of 18.15% in attack success rate and a success rate exceeding 95% on commercial black-box models, including GPT-4o and Gemini.

cs.CR↗

arXiv2026

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the susceptibility of agents to collective cognitive biases remains an underexplored issue. A compelling example is the Mandela effect, a phenomenon where groups collectively misremember past events as a result of false details reinforced through social influence and internalized misinformation. This vulnerability limits our understanding of memory bias in multi-agent systems and raises ethical concerns about the potential spread of misinformation. In this paper, we conduct a comprehensive study on the Mandela effect in LLM-based multi-agent systems, focusing on its existence, causing factors, and mitigation strategies. We propose MANBENCH, a novel benchmark designed to evaluate agent behaviors across four common task types that are susceptible to the Mandela effect, using five interaction protocols that vary in agent roles and memory timescales. We evaluate agents powered by several LLMs on MANBENCH to quantify the Mandela effect and analyze how different factors affect it. Moreover, we propose strategies to mitigate this effect, including prompt-level defenses (e.g., cognitive anchoring and source scrutiny) and model-level alignment-based defense, achieving an average 74.40% reduction in the Mandela effect compared to the baseline. Our findings provide valuable insights for developing more resilient and ethically aligned collaborative multi-agent systems. Code and dataset are available at https://github.com/bluedream02/Mandela-Effect.

cs.CL↗

arXiv2026

Contextual and Seasonal LSTMs for Time Series Anomaly Detection

Univariate time series (UTS), where each timestamp records a single variable, serve as crucial indicators in web systems and cloud servers. Anomaly detection in UTS plays an essential role in both data mining and system reliability management. However, existing reconstruction-based and prediction-based methods struggle to capture certain subtle anomalies, particularly small point anomalies and slowly rising anomalies. To address these challenges, we propose a novel prediction-based framework named Contextual and Seasonal LSTMs (CS-LSTMs). CS-LSTMs are built upon a noise decomposition strategy and jointly leverage contextual dependencies and seasonal patterns, thereby strengthening the detection of subtle anomalies. By integrating both time-domain and frequency-domain representations, CS-LSTMs achieve more accurate modeling of periodic trends and anomaly localization. Extensive evaluations on public benchmark datasets demonstrate that CS-LSTMs consistently outperform state-of-the-art methods, highlighting their effectiveness and practical value in robust time series anomaly detection.

cs.LG↗

arXiv2026

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation difficult. Most existing defenses depend on passive detection of suspicious suffixes, without leveraging the defender's inherent asymmetric ability to inject secrets and proactively conceal gaps. Motivated by this, we take a controllability-oriented perspective and develop a proactive defense that nudges attackers into a no-win dilemma: either they fall into defender-designed optimization traps and fail to produce an effective adversarial suffix, or they can succeed only by generating adversarial suffixes that carry distinctive, traceable fingerprints. We propose TrapSuffix, a lightweight fine-tuning approach that injects trap-aligned behaviors into the base model without changing the inference pipeline. TrapSuffix channels jailbreak attempts into these two outcomes by reshaping the model's response landscape to adversarial suffixes. Across diverse suffix-based jailbreak settings, TrapSuffix reduces the average attack success rate to below 0.01 percent and achieves an average tracing success rate of 87.9 percent, providing both strong defense and reliable traceability. It introduces no inference-time overhead and incurs negligible memory cost, requiring only 15.87 MB of additional memory on average, whereas state-of-the-art LLM-based detection defenses typically incur memory overheads at the 1e4 MB level, while composing naturally with existing filtering-based defenses for complementary protection.

cs.CR↗

arXiv2026

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks

Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have been developed to address this issue, they often exhibit limitations in effectiveness, interpretability, and generalizability, particularly when applied to LLM-based applications. To address these challenges, we introduce FraudShield, a novel framework designed to protect LLMs from fraudulent content by leveraging a comprehensive analysis of fraud tactics. Specifically, FraudShield constructs and refines a fraud tactic-keyword knowledge graph to capture high-confidence associations between suspicious text and fraud techniques. The structured knowledge graph augments the original input by highlighting keywords and providing supporting evidence, guiding the LLM toward more secure responses. Extensive experiments show that FraudShield consistently outperforms state-of-the-art defenses across four mainstream LLMs and five representative fraud types, while also offering interpretable clues for the model's generations.

cs.CR↗

arXiv2026

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models

While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components governing safety. Existing methods rely on local, greedy attribution that assumes independent component contributions. However, they overlook the cooperative interactions between different components in LLMs, such as attention heads, which jointly contribute to safety mechanisms. We propose \textbf{G}lobal \textbf{O}ptimization for \textbf{S}afety \textbf{V}ector Extraction (GOSV), a framework that identifies safety-critical attention heads through global optimization over all heads simultaneously. We employ two complementary activation repatching strategies: Harmful Patching and Zero Ablation. These strategies identify two spatially distinct sets of safety vectors with consistently low overlap, termed Malicious Injection Vectors and Safety Suppression Vectors, demonstrating that aligned LLMs maintain separate functional pathways for safety purposes. Through systematic analyses, we find that complete safety breakdown occurs when approximately 30\% of total heads are repatched across all models. Building on these insights, we develop a novel inference-time white-box jailbreak method that exploits the identified safety vectors through activation repatching. Our attack substantially outperforms existing white-box attacks across all test models, providing strong evidence for the effectiveness of the proposed GOSV framework on LLM safety interpretability.

cs.LG↗

arXiv2025

APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-Training

Provenance-based threat hunting identifies Advanced Persistent Threats (APTs) on endpoints by correlating attack patterns described in Cyber Threat Intelligence (CTI) with provenance graphs derived from system audit logs. A fundamental challenge in this paradigm lies in the modality gap -- the structural and semantic disconnect between provenance graphs and CTI reports. Prior work addresses this by framing threat hunting as a graph matching task: 1) extracting attack graphs from CTI reports, and 2) aligning them with provenance graphs. However, this pipeline incurs severe \textit{information loss} during graph extraction and demands intensive manual curation, undermining scalability and effectiveness. In this paper, we present APT-CGLP, a novel cross-modal APT hunting system via Contrastive Graph-Language Pre-training, facilitating end-to-end semantic matching between provenance graphs and CTI reports without human intervention. First, empowered by the Large Language Model (LLM), APT-CGLP mitigates data scarcity by synthesizing high-fidelity provenance graph-CTI report pairs, while simultaneously distilling actionable insights from noisy web-sourced CTIs to improve their operational utility. Second, APT-CGLP incorporates a tailored multi-objective training algorithm that synergizes contrastive learning with inter-modal masked modeling, promoting cross-modal attack semantic alignment at both coarse- and fine-grained levels. Extensive experiments on four real-world APT datasets demonstrate that APT-CGLP consistently outperforms state-of-the-art threat hunting baselines in terms of accuracy and efficiency.

cs.CR↗

arXiv2025

Breaking Isolation: A New Perspective on Hypervisor Exploitation via Cross-Domain Attacks

Hypervisors are under threat by critical memory safety vulnerabilities, with pointer corruption being one of the most prevalent and severe forms. Existing exploitation frameworks depend on identifying highly-constrained structures in the host machine and accurately determining their runtime addresses, which is ineffective in hypervisor environments where such structures are rare and further obfuscated by Address Space Layout Randomization (ASLR). We instead observe that modern virtualization environments exhibit weak memory isolation -- guest memory is fully attacker-controlled yet accessible from the host, providing a reliable primitive for exploitation. Based on this observation, we present the first systematic characterization and taxonomy of Cross-Domain Attacks (CDA), a class of exploitation techniques that enable capability escalation through guest memory reuse. To automate this process, we develop a system that identifies cross-domain gadgets, matches them with corrupted pointers, synthesizes triggering inputs, and assembles complete exploit chains. Our evaluation on 15 real-world vulnerabilities across QEMU and VirtualBox shows that CDA is widely applicable and effective.

cs.CR↗

arXiv2025

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?

Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLMs accurately recognize and comply with copyright regulations when encountering copyrighted content (i.e., user input, retrieved documents) in the context? Failure to comply with copyright regulations may lead to serious legal and ethical consequences, particularly when LVLMs generate responses based on copyrighted materials (e.g., retrieved book experts, news reports). In this paper, we present a comprehensive evaluation of various LVLMs, examining how they handle copyrighted content -- such as book excerpts, news articles, music lyrics, and code documentation when they are presented as visual inputs. To systematically measure copyright compliance, we introduce a large-scale benchmark dataset comprising 50,000 multimodal query-content pairs designed to evaluate how effectively LVLMs handle queries that could lead to copyright infringement. Given that real-world copyrighted content may or may not include a copyright notice, the dataset includes query-content pairs in two distinct scenarios: with and without a copyright notice. For the former, we extensively cover four types of copyright notices to account for different cases. Our evaluation reveals that even state-of-the-art closed-source LVLMs exhibit significant deficiencies in recognizing and respecting the copyrighted content, even when presented with the copyright notice. To solve this limitation, we introduce a novel tool-augmented defense framework for copyright compliance, which reduces infringement risks in all scenarios. Our findings underscore the importance of developing copyright-aware LVLMs to ensure the responsible and lawful use of copyrighted content.

cs.CL↗

arXiv2025

The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks

Deep neural networks (DNNs) underpin critical applications yet remain vulnerable to backdoor attacks, typically reliant on heuristic brute-force methods. Despite significant empirical advancements in backdoor research, the lack of rigorous theoretical analysis limits understanding of underlying mechanisms, constraining attack predictability and adaptability. Therefore, we provide a theoretical analysis targeting backdoor attacks, focusing on how sparse decision boundaries enable disproportionate model manipulation. Based on this finding, we derive a closed-form, ambiguous boundary region, wherein negligible relabeled samples induce substantial misclassification. Influence function analysis further quantifies significant parameter shifts caused by these margin samples, with minimal impact on clean accuracy, formally grounding why such low poison rates suffice for efficacious attacks. Leveraging these insights, we propose Eminence, an explainable and robust black-box backdoor framework with provable theoretical guarantees and inherent stealth properties. Eminence optimizes a universal, visually subtle trigger that strategically exploits vulnerable decision boundaries and effectively achieves robust misclassification with exceptionally low poison rates (< 0.1%, compared to SOTA methods typically requiring > 1%). Comprehensive experiments validate our theoretical discussions and demonstrate the effectiveness of Eminence, confirming an exponential relationship between margin poisoning and adversarial boundary manipulation. Eminence maintains > 90% attack success rate, exhibits negligible clean-accuracy loss, and demonstrates high transferability across diverse models, datasets and scenarios.

cs.LG↗

arXiv2025

DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication

In this paper, we propose a Differentially Private Stochastic Gradient Push with Compressed communication (termed DP-CSGP) for decentralized learning over directed graphs. Different from existing works, the proposed algorithm is designed to maintain high model utility while ensuring both rigorous differential privacy (DP) guarantees and efficient communication. For general non-convex and smooth objective functions, we show that the proposed algorithm achieves a tight utility bound of $\mathcal{O}\left( \sqrt{d\log \left( \frac{1}δ \right)}/(\sqrt{n}Jε) \right)$ ($J$ and $d$ are the number of local samples and the dimension of decision variables, respectively) with $\left(ε, δ\right)$-DP guarantee for each node, matching that of decentralized counterparts with exact communication. Extensive experiments on benchmark tasks show that, under the same privacy budget, DP-CSGP achieves comparable model accuracy with significantly lower communication cost than existing decentralized counterparts with exact communication.

cs.LG↗

arXiv2025

A Survey of Operating System Kernel Fuzzing

The Operating System (OS) kernel is foundational in modern computing, especially with the proliferation of diverse computing devices. However, its development also comes with vulnerabilities that can lead to severe security breaches. Kernel fuzzing, a technique used to uncover these vulnerabilities, poses distinct challenges when compared to user-space fuzzing. These include the complexity of configuring the testing environment and addressing the statefulness inherent to both the kernel and the fuzzing process. Despite the significant interest from the community, a comprehensive understanding of kernel fuzzing remains lacking, hindering further progress in the field. In this paper, we present the first systematic study focused specifically on OS kernel fuzzing. We begin by outlining the unique challenges of kernel fuzzing, which distinguish it from those in user space. Following this, we summarize the progress of 107 academic studies from top-tier venues between 2017 and 2025. To structure this analysis, we introduce a stage-based fuzzing model and a novel fuzzing taxonomy that highlights nine core functionalities unique to kernel fuzzing. Each of these functionalities is examined in conjunction with the methodological approaches employed to address them. Finally, we identify remaining gaps in addressing challenges and outline promising directions to guide forthcoming research in kernel security.

cs.CR↗

arXiv2025

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finance. Recent studies reveal that adversaries can implant backdoors into DRL agents during the training phase. These backdoors can later be activated by specific triggers during deployment, compelling the agent to execute targeted actions and potentially leading to severe consequences, such as drone crashes or vehicle collisions. However, existing backdoor attacks utilize simplistic and heuristic trigger configurations, overlooking the critical impact of trigger design on attack effectiveness. To address this gap, we introduce TooBadRL, the first framework to systematically optimize DRL backdoor triggers across three critical aspects: injection timing, trigger dimension, and manipulation magnitude. Specifically, we first introduce a performance-aware adaptive freezing mechanism to determine the injection timing during training. Then, we formulate trigger selection as an influence attribution problem and apply Shapley value analysis to identify the most influential trigger dimension for injection. Furthermore, we propose an adversarial input synthesis method to optimize the manipulation magnitude under environmental constraints. Extensive evaluations on three DRL algorithms and nine benchmark tasks demonstrate that TooBadRL outperforms five baseline methods in terms of attack success rate while only slightly affecting normal task performance. We further evaluate potential defense strategies from detection and mitigation perspectives. We open-source our code to facilitate reproducibility and further research.

cs.CR↗

arXiv2025

Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio

Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content. Realizing such threats poses two core challenges: (1) LALM safety alignment frequently rejects harmful prompts, yet existing jailbreak attacks are ill-suited for TTS because these systems are designed to faithfully vocalize any input text, and (2) real-world deployment pipelines often employ input/output filters that block harmful text and audio. We present HARMGEN, a suite of five attacks organized into two families that address these challenges. The first family employs semantic obfuscation techniques (Concat, Shuffle) that conceal harmful content within text. The second leverages audio-modality exploits (Read, Spell, Phoneme) that inject harmful content through auxiliary audio channels while maintaining benign textual prompts. Through evaluation across five commercial LALMs-based TTS systems and three datasets spanning two languages, we demonstrate that our attacks substantially reduce refusal rates and increase the toxicity of generated speech. We further assess both reactive countermeasures deployed by audio-streaming platforms and proactive defenses implemented by TTS providers. Our analysis reveals critical vulnerabilities: deepfake detectors underperform on high-fidelity audio; reactive moderation can be circumvented by adversarial perturbations; while proactive moderation detects 57-93% of attacks. Our work highlights a previously underexplored content-centric misuse vector for TTS and underscore the need for robust cross-modal safeguards throughout training and deployment.

cs.SD↗