We have 12 of 369 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The proposed SUA-Arena, which implements 6 attack strategies and contains 188 test cases, finds that all of them are vulnerable to show-up attacks and shows that multi-agent systems need explicit mechanisms for enforcing authority boundaries.
Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos, posing threats of misuse as anyone can turn personal photos into fabricated videos without consent. A promising solution is to proactively add an adversarial perturbation to the image before release,...
Large language models (LLMs) increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent leakage. Existing extracti...
Experiments show that SKILLLITE improves malicious Skill detection across different compact LLM backbones and outperforms existing representative auditing baselines, and generalizes to behaviorally confirmed in-the-wild malicious Skills.
RAPID is proposed, a self-referenced latent maximization framework that removes external dependencies and encourages the same model update to induce consistently disruptive effects across training samples, thereby improving reachability and establishing a paradigm for real-time protection against unauthorized distillat...
ECLIPSE is a self-evolving and stealthy prompt-injection framework for long-horizon agentic systems that achieves up to 96.7% attack success without defense and 69.2% under the common safety filter, exceeding the strongest baseline by 27.5% in the defended setting.
As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by...
ASCon is proposed, a direction-aware reciprocal \textbf{A}gent--\textbf{S}tep \textbf{Con}textualization model for multiple failure attribution targets that introduces direction-aware graph attention to model execution context, masked step-to-agent attention to construct behavior-aware agent representations, and agent-...
Results suggest that persistent memory can turn ordinary external processing into a practical pathway for long-term agent compromise.
This paper proposes LeakGauge, which probes this response by appending a suffix that gauges leakage behavior and mapping its prefill token probabilities to an attack-risk score, and shows that the risk score is sensitive to an internal leakage-related direction.
This work proposes Sampled-BPE, a lightweight token-level auditing pipeline that sample a small subset and train BPE tokenizer to surface polluted tokens, and releases a hierarchical Chinese web token dataset with 660k+ token records, organized as trees to support review and tracing of pollution.
A probe-gated reasoning-based defense is introduced to bridge a knowledge-action gap in agentic LLMs when they are exposed to IPI attacks, and an analysis framework is introduced that identifies natural-language explanations strongly correlated with probe-captured signals.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
