Lune

Profiles2020-2026

Bo Li

University of Illinois at Urbana-Champaign

72Papers
45Last author
142Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers72

  1. ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play AttacksAuthor 7 of 7ICLR 2026 · 5 citations
  2. Adversarial Attacks against Closed-Source MLLMs via Feature Optimal AlignmentAuthor 9 of 10NeurIPS 2025 · 49 citations
  3. C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming GuardrailsAuthor 3 of 3NeurIPS 2025 · 4 citations
  4. COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic AttacksAuthor 5 of 5AAAI 2025 · 2 citations
  5. AdvAgent: Controllable Blackbox Red-teaming on Web AgentsAuthor 8 of 8ICML 2025
  6. AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language ModelsAuthor 3 of 3ICLR 2025
  7. MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation ModelsAuthor 24 of 25ICLR 2025
  8. R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical ReasoningAuthor 2 of 2ICLR 2025
  9. Robust Prompt Optimization for Defending Language Models Against Jailbreaking AttacksAuthor 2 of 3NeurIPS 2024 · 198 citations
  10. C-RAG: Certified Generation Risks for Retrieval-Augmented Language ModelsAuthor 5 of 5ICML 2024 · 33 citations
  11. Data Free Backdoor AttacksAuthor 7 of 8NeurIPS 2024 · 12 citations
  12. Certifiably Byzantine-Robust Federated Conformal PredictionAuthor 5 of 5ICML 2024 · 8 citations
  13. MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of VideosAuthor 11 of 12CVPR 2024 · 7 citations
  14. KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph DataAuthor 7 of 8CCS 2024 · 5 citations
  15. TextGuard: Provable Defense against Backdoor Attacks on Text ClassificationAuthor 4 of 7NDSS 2024
  16. Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at HandAuthor 7 of 7NeurIPS 2023 · 93 citations
  17. DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial PurificationAuthor 3 of 3NeurIPS 2023 · 66 citations
  18. IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIAuthor 5 of 6NeurIPS 2023 · 46 citations
  19. Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare MaximizationAuthor 4 of 5NeurIPS 2023 · 37 citations
  20. FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated LearningAuthor 7 of 8NeurIPS 2023 · 32 citations
  21. CBD: A Certified Backdoor Detector Based on Local Dominant ProbabilityAuthor 3 of 3NeurIPS 2023 · 29 citations
  22. UMD: Unsupervised Model Detection for X2X Backdoor AttacksAuthor 3 of 3ICML 2023 · 27 citations
  23. Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning AttacksAuthor 5 of 5CCS 2023 · 12 citations
  24. On the Robustness of Safe Reinforcement Learning under Observational PerturbationsAuthor 6 of 9ICLR 2023 · 9 citations
  25. RAB: Provable Robustness Against Backdoor AttacksAuthor 5 of 5S&P 2023
  26. TrojDiff: Trojan Attacks on Diffusion Models with Diverse TargetsAuthor 4 of 4CVPR 2023
  27. Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright ProtectionAuthor 6 of 6NeurIPS 2022 · 161 citations
  28. General Cutting Planes for Bound-Propagation-Based Neural Network VerificationAuthor 5 of 8NeurIPS 2022 · 154 citations
  29. LINKTELLER: Recovering Private Edges from Graph Neural Networks via Influence AnalysisAuthor 4 of 4S&P 2022 · 125 citations
  30. Copy, Right? A Testing Framework for Copyright Protection of Deep Learning ModelsAuthor 8 of 11S&P 2022 · 94 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines