recent

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships

Vision-Language Models (VLMs) are increasingly adopted in practical applications, but remain vulnerable to adversarial perturbations. Existing adversarial fine-tuning methods often rely on one-to-one image-text supervision and may overfit to narrow …

Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language Models

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training (AT) methods …

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models

Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a novel risk of …

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off

Although adversarial training has been the state-of-the-art approach to defend against adversarial examples (AEs), it suffers from a robustness-accuracy trade-off, where high robustness is achieved at the cost of clean accuracy. In this work, we …

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection

Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing risks in its …

Beyond In-Domain Scenarios: Robust Density-Aware Calibration

Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on in-domain …

Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently

Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model’s predictions. However, the transferability has not been understood in …