Mintong Kang

7

Papers

200

Total Citations

Papers (7)

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

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

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

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

FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Certifiably Byzantine-Robust Federated Conformal Prediction