Jie Shi

7

Papers

67

Total Citations

Papers (7)

Small Model Can Self-Correct

ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

Multi-Turn Jailbreaking Large Language Models via Attention Shifting

PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection

Shape Analysis With Hyperbolic Wasserstein Distance

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

MExMI: Pool-based Active Model Extraction Crossover Membership Inference