pith. sign in

Tianhang Zheng

Identifiers

No identifiers captured yet.

Papers (9)

  1. Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training cs.LG · 2026 · author #3
  2. Mitigating Error Amplification in Fast Adversarial Training cs.LG · 2026 · author #4
  3. Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models cs.CR · 2026 · author #3
  4. Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache cs.CR · 2026 · author #5
  5. Poisoning with A Pill: Circumventing Detection in Federated Learning cs.LG · 2024 · author #4
  6. Data Poisoning Attack against Knowledge Graph Embedding cs.LG · 2019 · author #2
  7. FID: Function Modeling-based Data-Independent and Channel-Robust Physical-Layer Identification cs.CR · 2019 · author #1
  8. Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples Only cs.LG · 2018 · author #1
  9. Distributionally Adversarial Attack cs.LG · 2018 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors