Profiles2022-2026
Mintong Kang
University of Illinois, Urbana-Champaign
12Papers
0Last author
10Unique co-authors
9First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers12
- ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play AttacksAuthor 3 of 7ICLR 2026 · 5 citations
- C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming GuardrailsAuthor 1 of 3NeurIPS 2025 · 4 citations
- AdvAgent: Controllable Blackbox Red-teaming on Web AgentsAuthor 2 of 8ICML 2025
- AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language ModelsAuthor 1 of 3ICLR 2025
- FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent GuidanceAuthor 1 of 9EMNLP 2025
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation ModelsAuthor 5 of 25ICLR 2025
- R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical ReasoningAuthor 1 of 2ICLR 2025
- C-RAG: Certified Generation Risks for Retrieval-Augmented Language ModelsAuthor 1 of 5ICML 2024 · 33 citations
- COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic CircuitsAuthor 1 of 4ICLR 2024 · 12 citations
- Certifiably Byzantine-Robust Federated Conformal PredictionAuthor 1 of 5ICML 2024 · 8 citations
- DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial PurificationAuthor 1 of 3NeurIPS 2023 · 66 citations
- Certifying Some Distributional Fairness with Subpopulation DecompositionAuthor 1 of 5NeurIPS 2022 · 17 citations
