4 papers
Prototype-Guided Robust Learning against Backdoor Attacks
Wei Guo, Maura Pintor, Ambra Demontis +1
Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input…
Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
Wei Guo, Fabio Brau, Maura Pintor +2
Semi-structured (2:4) sparsity is a widely adopted pruning method in modern hardware and software ecosystems (e.g., NVIDIA Sparse Tensor Cores and PyTorch), achieving up to 2X fast…
Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach
Weiran Guo, Bing Bo, Shaoxiang Wu +1
Function call capabilities have become crucial for Large Language Models (LLMs), enabling them to interact more effectively with external tools and APIs. Existing methods for impro…
JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example
Benedetta Tondi, Wei Guo, Niccolò Pancino +1
Most of the approaches proposed so far to craft targeted adversarial examples against Deep Learning classifiers are highly suboptimal and typically rely on increasing the likelihoo…