Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulnerability. In this work, we introduce BITE (BIas exploraTion and Exploitation), a black-box adversarial framework that learns semantics-preserving edits to mislead an LLM judge and artificially inflate the scores it assigns. We cast the selection of stylistic edits as a contextual bandit problem and use a LinUCB policy to adaptively choose edits that maximize the judge's score without access to model parameters or gradients. Empirically, we test BITE across a diverse range of LLM judges and tasks, including both pointwise and pairwise comparisons on chatbot leaderboards and AI-reviewer benchmarks. BITE achieves an attack success rate exceeding 65% and raises scores by 1-2 points on a 9-point scale, all while preserving semantic equivalence. We further assess the attack's stealthiness, showing that BITE evades standard style-control methods and several detection baselines. Our findings expose a fundamental weakness in the LLM-as-a-judge paradigm and motivate robust, attack-aware evaluation. Our code is available at https://github.com/xianglinyang/llm-as-a-judge-attack.

MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily manipulate the tool metadata, which is easily detectable by auditing and may lose effectiveness as modern agents increasingly adopt memory modules to refine tool selection policies through accumulated experience. This paper proposes MemMorph, the first attack that bias tool selection by poisoning the agent's long-term memory. Rather than explicitly dictating the tool invocation decision, MemMorph injects a small number of crafted records that are disguised as technical facts, incident reports, and operational policies. These poisoned records reshape the agent's contextual perception and decision-making process, leading it to autonomously infer and select the tool preferred by the attacker. Experiments across 3 benchmarks, 10 agent backbones, and 3 memory-module implementations show that MemMorph achieves up to 85.9% attack success rate with only three injected records, outperforming the strongest baseline by up to 25% while retaining potency under 3 representative defenses. Our findings expose long-term memory as a critical and under-explored attack surface in tool-augmented agents, urging the development of memory-level integrity safeguards.

LeakDojo: Decoding the Leakage Threats of RAG Systems

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems grow more complex and LLMs exhibit stronger instruction-following capabilities, existing studies fall short of systematically assessing RAG leakage risks. We present LeakDojo, a configurable framework for controlled evaluation of RAG leakage. Using LeakDojo, we benchmark six existing attacks across fourteen LLMs, four datasets, and diverse RAG systems. Our study reveals that (1) query generation and adversarial instructions contribute independently to leakage, with overall leakage well approximated by their product; (2) stronger instruction-following capability correlates with higher leakage risk; and (3) improvements in RAG faithfulness can introduce increased leakage risk. These findings provide actionable insights for understanding and mitigating RAG leakage in practice. Our codebase is available at https://github.com/yeasen-z/LeakDojo.

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat, auditory prompt injection, under realistic constraints of audio data-only access and strong perceptual stealth. To systematically analyze this threat, we propose \textit{AudioHijack}, a general framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs. \textit{AudioHijack} employs sampling-based gradient estimation for end-to-end optimization across diverse models, bypassing non-differentiable audio tokenization. Through attention supervision and multi-context training, it steers model attention toward adversarial audio and generalizes to unseen user contexts. We also design a convolutional blending method that modulates perturbations into natural reverberation, making them highly imperceptible to users. Extensive experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 misbehavior categories, achieving average success rates of 79\%-96\% on unseen user contexts with high acoustic fidelity. Real-world studies demonstrate that commercial voice agents from Mistral AI and Microsoft Azure can be induced to execute unauthorized actions on behalf of users. These findings expose critical vulnerabilities in LALMs and highlight the urgent need for dedicated defense.

AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications. Penetration testing is a widely adopted approach that validates exploitability by launching concrete attacks against known vulnerabilities in real-world black-box systems. However, existing approaches often fail to automatically generate reliable exploits, limiting their effectiveness in practical security assessment. This limitation mainly stems from two issues: (1) precisely triggering vulnerabilities with correct technical details, and (2) adapting exploits to diverse real-world deployment settings. In this paper, we propose AutoEG, a fully automated multi-agent framework for exploit generation targeting black-box web applications. AutoEG has two phases: First, AutoEG extracts precise vulnerability trigger logic from unstructured vulnerability information and encapsulates it into reusable trigger functions. Second, AutoEG uses trigger functions for concrete attack objectives and iteratively refines exploits through feedback-driven interaction with the target application. We evaluate AutoEG on 104 real-world vulnerabilities with 29 attack objectives, resulting in 660 exploitation tasks and 55,440 exploit attempts. AutoEG achieves an average success rate of 82.41%, substantially outperforming state-of-the-art baselines, whose best performance reaches only 32.88%.

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution

We identify a critical security vulnerability in mainstream Claw personal AI agents: untrusted content encountered during heartbeat-driven background execution can silently pollute agent memory and subsequently influence user-facing behavior without the user's awareness. This vulnerability arises from an architectural design shared across the Claw ecosystem: heartbeat background execution runs in the same session as user-facing conversation, so content ingested from any external source monitored in the background (including email, message channels, news feeds, code repositories, and social platforms) can enter the same memory context used for foreground interaction, often with limited user visibility and without clear source provenance. We formalize this process as an Exposure (E) $\rightarrow$ Memory (M) $\rightarrow$ Behavior (B) pathway: misinformation encountered during heartbeat execution enters the agent's short-term session context, potentially gets written into long-term memory, and later shapes downstream user-facing behavior. We instantiate this pathway in an agent-native social setting using MissClaw, a controlled research replica of Moltbook. We find that (1) social credibility cues, especially perceived consensus, are the dominant driver of short-term behavioral influence, with misleading rates up to 61%; (2) routine memory-saving behavior can promote short-term pollution into durable long-term memory at rates up to 91%, with cross-session behavioral influence reaching 76%; (3) under naturalistic browsing with content dilution and context pruning, pollution still crosses session boundaries. Overall, prompt injection is not required: ordinary social misinformation is sufficient to silently shape agent memory and behavior under heartbeat-driven background execution.

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However, its adoption has been limited by the lack of high-quality draft models and scalable training infrastructure. We introduce SpecForge, an open-source, production-oriented framework for training speculative decoding models with full support for EAGLE-3. SpecForge incorporates target-draft decoupling, hybrid parallelism, optimized training kernels, and integration with production-grade inference engines, enabling up to 9.9x faster EAGLE-3 training for Qwen3-235B-A22B. In addition, we release SpecBundle, a suite of production-grade EAGLE-3 draft models trained with SpecForge for mainstream open-source LLMs. Through a systematic study of speculative decoding training recipes, SpecBundle addresses the scarcity of high-quality drafts in the community, and our draft models achieve up to 4.48x end-to-end inference speedup on SGLang, establishing SpecForge as a practical foundation for real-world speculative decoding deployment.

State-Dependent Safety Failures in Multi-Turn Language Model Interaction

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study safety failures from a state-space perspective and show that many multi-turn failures arise from structured contextual state evolution rather than isolated prompt vulnerabilities. We introduce STAR, a state-oriented diagnostic framework that treats dialogue history as a state transition operator and enables controlled analysis of safety behavior along interaction trajectories. Rather than optimizing attack strength, STAR provides a principled probe of how aligned models traverse the safety boundary under autoregressive conditioning. Across multiple frontier language models, we find that systems that appear robust under static evaluation can undergo rapid and reproducible safety collapse under structured multi-turn interaction. Mechanistic analysis reveals monotonic drift away from refusal-related representations and abrupt phase transitions induced by role-conditioned context. Together, these findings motivate viewing language model safety as a dynamic, state-dependent process defined over conversational trajectories.

TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking

We propose TRACE, a structure-aware framework leveraging diffusion models for localized character encoding to embed data. Unlike existing methods that rely on edge features or pre-defined codebooks, TRACE exploits character structures that provide inherent resistance to noise interference due to their stability and unified representation across diverse characters. Our framework comprises three key components: (1) adaptive diffusion initialization that automatically identifies handle points, target points, and editing regions through specialized algorithms including movement probability estimator (MPE), target point estimation (TPE) and mask drawing model (MDM), (2) guided diffusion encoding for precise movement of selected point, and (3) masked region replacement with a specialized loss function to minimize feature alterations after the diffusion process. Comprehensive experiments demonstrate \name{}'s superior performance over state-of-the-art methods, achieving more than 5 dB improvement in PSNR and 5\% higher extraction accuracy following cross-media transmission. \name{} achieves broad generalizability across multiple languages and fonts, making it particularly suitable for practical document security applications.

Understanding and Enhancing Encoder-based Adversarial Transferability against Large Vision-Language Models

Large vision-language models (LVLMs) have achieved impressive success across multimodal tasks, but their reliance on visual inputs exposes them to significant adversarial threats. Existing encoder-based attacks perturb the input image by optimizing solely on the vision encoder, rather than the entire LVLM, offering a computationally efficient alternative to end-to-end optimization. However, their transferability across different LVLM architectures in realistic black-box scenarios remains poorly understood. To address this gap, we present the first systematic study towards encoder-based adversarial transferability in LVLMs. Our contributions are threefold. First, through large-scale benchmarking over eight diverse LVLMs, we reveal that existing attacks exhibit severely limited transferability. Second, we perform in-depth analysis, disclosing two root causes that hinder the transferability: (1) inconsistent visual grounding across models, where different models focus their attention on distinct regions; (2) redundant semantic alignment within models, where a single object is dispersed across multiple overlapping token representations. Third, we propose Semantic-Guided Multimodal Attack (SGMA), a novel framework to enhance the transferability. Inspired by the discovered causes in our analysis, SGMA directs perturbations toward semantically critical regions and disrupts cross-modal grounding at both global and local levels. Extensive experiments across different victim models and tasks show that SGMA achieves higher transferability than existing attacks. These results expose critical security risks in LVLM deployment and underscore the urgent need for robust multimodal defenses.