Shouling Ji

MTGuard effectively reduces harmful tool use in LLM agents, combining static and dynamic analysis to enhance security without sacrificing performance.

Backdoor attacks can generalize across trigger families, with Lilith achieving high success rates while preserving benign model performance.

Flipping just a few bits can stealthily manipulate LLMs to induce significant cognitive biases, posing a serious threat to decision-making integrity.

All 15 evaluated x402 facilitators have critical security flaws that could lead to severe financial losses for merchants and users alike.

Self-evolving LLMs can amplify adversarial threats, making every known attack lineage-persistent and exposing critical vulnerabilities that static defenses can't address.

Over 80% of real-world LLM applications leak sensitive prompts, but a new defense, AREA, not only mitigates this risk but also boosts usability by over 33%.

Malicious LoRA plugins can hijack public sentiment and spread harmful content, achieving nearly 100% success rates without detection.

FLAME uncovers a hidden statistical energy gap in AI-generated images, enabling precise localization of forgeries that traditional methods miss.

Forget jailbreaking with surface tokens – this new backdoor method steers internal representations for persistent, stealthy attacks that are much harder to detect.

Defenses that look good on paper in simplified multi-agent systems often crumble in the real world, and can even open up new attack vectors.