Workshop Program Wednesday June 24, 2026 (All times are in Local Time)
| Time | Program Details |
|---|---|
|
Session 1: Opening & Keynote Session I
Session Chairs: Leo Zhang & Yifeng Zhang | Join Teams Meeting
|
|
| 09:20 - 09:25 | Opening |
| 09:25 - 10:25 | Keynote 1: Securing AI, Abusing AI, Trusting AI: Three Views of Security and Privacy in Machine Learning Models and Applications Prof. Bo Luo |
| 10:25 - 11:00 | Coffee Break |
|
Session 2: Technical Session I
Session Chair: Jianying Zhou
|
|
| 11:00 - 11:15 | ACEraser: Environment Forgetting in Actor-Critic Reinforcement Learning through Influence FunctionJoshua Maccoby and Wendy Hui Wang |
| 11:15 - 11:30 | Filtering Adversarial Examples in Binary Function Similarity ModelsAnna Paola Giancaspro, Gianluca Capozzi and Giuseppe Antonio Di Luna |
| 11:30 - 11:45 | Street-Legal Physical-World Adversarial Rim for License PlatesNikhil Kalidasu and Sahana Ganapathy |
| 11:45 - 12:00 | Can Large Language Models Evade CNN-Based Malware Detection? A Study of Functionality-Preserving Adversarial AssemblyMd Mashrur Arifin, Brodie Abrew, Devyn Hubbs, Ahmed Saif Muntaseer and Jyh-Haw Yeh |
| 12:00 - 12:15 | Detection and Explanation of PowerShell Malware with Large Language ModelsMeng Wang, Emma Topolovec, Beatrice Arana, Naga Venkata Prasanna Sai Gupta Chimakurthy Kuladeep, Zhaohan Xi, Guanhua Yan, Xiaokui Shu, Scott Stoller and Ping Yang |
| 12:15 - 14:00 | Lunch Break |
|
Session 3: Keynote & Technical Session II
Session Chair: Leo Zhang | Join Teams Meeting
|
|
| 14:00 - 15:00 | Keynote 2: Prompt Injection in LLM Agents A/Prof. Neil Gong |
| 15:00 - 15:15 | Membership Inference Attacks Against Video Large Language ModelsWei Song, Yuxin Cao, Ziqi Ding, Yi Liu, Gelei Deng and Yuekang Li |
| 15:15 - 15:30 | Variational Feature Compression for Model-Specific RepresentationsZinan Guo, Zihan Wang, Chuan Yan, Liuhuo Wan, Ethan Ma and Guangdong Bai |
| 15:30 - 16:00 | Coffee Break |
|
Session 4: Technical Session III
Session Chair: Fuyi Wang | Join Teams Meeting
|
|
| 16:00 - 16:15 | SENTINEL: Self-Supervised Continual Anomaly Detection for Securing LLM Agent SystemsJake Garnier |
| 16:15 - 16:30 | AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy MitigationJunchen Ding, Jialiang Dong, Yichen Zhu, Yi Liu, Gelei Deng, Willy Susilo, Siqi Ma and Yuekang Li |
| 16:30 - 16:45 | Privacy-Preserving Fairness Evaluation using Fully Homomorphic EncryptionDivyesh Saglani, Imtiyazuddin Shaik, Rajan M. A., Srividhya Sankepally and Bharat Ratnala |
Presentation Format
- Regular Paper: 12 minutes presentation + 3 minutes Q&A
- Keynote: 50 minutes presentation + 10 minutes Q&A
Microsoft Teams Meeting
- Join
- Join Microsoft Teams Meeting
- Meeting ID
- 454 392 522 017 83
- Passcode
- RD75rd37