Paper-Conference

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

Controllable Spoofing Attacks on Visual SLAM in Robotic Vehicles

Novel controllable spoofing attacks targeting Visual SLAM systems in robotic vehicles.

Dec 1, 2025

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models

Revealing and analyzing text bias in Large Audio-Language Models when audio and text inputs disagree.

Nov 1, 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

Detecting Perception-Based Attacks using Visual Odometry: Inconsistency Modeling and Checking on Robotic States

ICRA 2025 work on detecting perception-based attacks against robotic systems through visual-odometry consistency checks.

May 19, 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

PhyScout: Detecting Sensor Spoofing Attacks via Spatio-temporal Consistency

A novel detection mechanism for sensor spoofing attacks using spatio-temporal consistency analysis.

Oct 14, 2024