AI Security

What Makes a Good LLM Agent for Real-world Penetration Testing?

A 2026 study of real-world LLM penetration testing agents and Excalibur, a difficulty-aware agent for end-to-end attack planning.

Feb 19, 2026

Excalibur

Excalibur is a difficulty-aware LLM agent design for real-world penetration testing. It couples typed tooling, retrieval-augmented security knowledge, task difficulty assessment, and evidence-guided attack tree search to reduce planning failures in multi-step penetration testing tasks.

Feb 19, 2026

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

A large-scale empirical study of security vulnerabilities in AI-agent skill ecosystems.

Jan 15, 2026

Safety Snowball Agent

Safety Snowball Agent is an agent-based framework for evaluating how safe visual inputs can combine into unsafe behavior in large vision-language models. The framework accompanies the NeurIPS 2025 paper “Safe + Safe = Unsafe?” and probes a multimodal jailbreak mechanism that differs from traditional adversarial-image attacks.

Dec 2, 2025

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

NeurIPS 2025 work showing how safe images can combine into multimodal jailbreaks through the Safety Snowball effect.

Dec 2, 2025

RSafe: Incentivizing Proactive Reasoning to Build Robust and Adaptive LLM Safeguards

NeurIPS 2025 work on adaptive reasoning-based safeguards for robust LLM safety moderation.

Dec 2, 2025

Oedipus: LLM-enchanced Reasoning CAPTCHA Solver

An LLM-enhanced framework demonstrating vulnerabilities in reasoning-based CAPTCHA systems through AI-powered solving.

Oct 1, 2025

IllusionCAPTCHA: A CAPTCHA based on Visual Illusion

A WWW 2025 CAPTCHA design that uses visual illusions to create human-friendly but AI-hard verification tasks.

Apr 28, 2025

Efficient Detection of Toxic Prompts in Large Language Models

ASE 2024 work on efficient greybox detection of toxic prompts for large language models.

Oct 27, 2024

VisionGuard: Secure and Robust Visual Perception of Autonomous Vehicles in Practice

A comprehensive framework for securing visual perception systems in autonomous vehicles against adversarial attacks.

Oct 14, 2024