(2024). SoK: Pitfalls in Evaluating Black-Box Attacks. In IEEE SaTML 2024.

PDF Cite Code

(2023). What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?. In NeurIPS 2023.

PDF Cite Poster

(2023). Manipulating Transfer Learning for Property Inference. In CVPR 2023.

PDF Cite Code Video

(2022). Poisoning Attacks and Subpopulation Susceptibility. In VISxAI 2022 (Best Paper Award).

PDF Cite Code

(2022). Stealthy Backdoors as Compression Artifacts. In TIFS 2022.

PDF Cite Code

(2021). Model-Targeted Poisoning Attacks with Provable Convergence. In ICML, 2021.

PDF Cite Code Poster Slides

(2019). Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries. In Usenix Security 2020.

PDF Cite Code Slides Video