Follow
Tingwei Zhang
Tingwei Zhang
PhD student, Cornell University
Verified email at cornell.edu - Homepage
Title
Cited by
Cited by
Year
Adversarial Illusions in {Multi-Modal} Embeddings
T Zhang, R Jha, E Bagdasaryan, V Shmatikov
33rd USENIX Security Symposium (USENIX Security 24), 2024
82024
Sok: Pitfalls in evaluating black-box attacks
F Suya, A Suri, T Zhang, J Hong, Y Tian, D Evans
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 387-407, 2024
72024
Controlled generation of natural adversarial documents for stealthy retrieval poisoning
C Zhang, T Zhang, V Shmatikov
arXiv preprint arXiv:2410.02163, 2024
22024
Soft prompts go hard: Steering visual language models with hidden meta-instructions
T Zhang, C Zhang, JX Morris, E Bagdasarian, V Shmatikov
arXiv preprint arXiv:2407.08970, 2024
22024
Adversarial Hubness in Multi-Modal Retrieval
T Zhang, F Suya, R Jha, C Zhang, V Shmatikov
arXiv preprint arXiv:2412.14113, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–5