Mintong Kang

ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis

$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails

EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models

AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents

FairGen: controlling fair generations in diffusion models via adaptive latent guidance