The DeFake team went to USENIX Security 2026 in Baltimore, Maryland, from August 12 to 14, 2026. It was a good chance to catch up on the latest security and privacy research and to connect with researchers working on related problems. The team presented four posters.
Poster presentations
- Ishmam Bin Rofi, Y. Kelly Wu, Saniat Sohrawardi and Ersin Uzun. We are quite bad at this!
- Palavi V. Bhole, Y. Kelly Wu and Ersin Uzun. Toward Usable AI Transparency Signals.
- Shaikh Akib Shahriyar, Ben Brown, Armon Barton, Ning Zhang and Matthew Wright. How Many Queries Does It Take to Break a Deepfake Detector? Preliminary Findings from a Cost-Aware Robustness Audit.
- Y. Kelly Wu, Saniat J. Sohrawardi, Ersin Uzun and Matthew Wright. The Techniques are Ready. Is the Vocabulary?
