|
Workshop
|
|
Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
|
|
|
Workshop
|
|
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
|
|
|
Poster
|
Thu 13:30
|
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
Zhen Xiang · Zidi Xiong · Bo Li
|
|
|
Workshop
|
|
Why do universal adversarial attacks work on large language models?: Geometry might be the answer
|
|
|
Workshop
|
|
Like Oil and Water: Group Robustness and Poisoning Defenses Don’t Mix
|
|
|
Workshop
|
|
Title: Ignore the Law: The Legal Risks of Prompt Injection Attacks on Large Language Models; Author(s): Ram Shankar Siva Kumar, Jonathon Penney
|
|
|
Workshop
|
|
Backdoor Attacks for In-Context Learning with Language Models
|
|
|
Workshop
|
|
Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats
Xuandong Zhao · Kexun Zhang · Yu-Xiang Wang · Lei Li
|
|
|
Workshop
|
|
Introducing Vision into Large Language Models Expands Attack Surfaces and Failure Implications
|
|
|
Workshop
|
|
Transferable Adversarial Perturbations between Self-Supervised Speech Recognition Models
Raphaël Olivier · Hadi Abdullah · Bhiksha Raj
|
|
|
Workshop
|
|
Black Box Adversarial Prompting for Foundation Models
|
|
|
Workshop
|
|
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
Vijay Lingam · Mohammad Sadegh Akhondzadeh · Aleksandar Bojchevski
|
|
