In a backdoor attack, an adversary injects corrupted data into a model's training dataset in
order to gain control over its predictions on images with a specific attacker-defined trigger. A …

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced
by attackers, is becoming increasingly critical for machine learning security and integrity …

Backdoor defenses have been studied to alleviate the threat of deep neural networks
(DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt …

Abstract Contrastive Vision-Language Pre-training known as CLIP has shown promising
effectiveness in addressing downstream image recognition tasks. However recent works …

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor
attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be …

As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

Deep neural networks (DNNs) have found widespread applications in interpreting remote
sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are …

Recent studies demonstrated that deep neural networks (DNNs) are vulnerable to backdoor
attacks. The attacked model behaves normally on benign samples, while its predictions are …

Deep learning, especially deep neural networks (DNNs), has been widely and successfully
adopted in many critical applications for its high effectiveness and efficiency. The rapid …

Large vision-language models (VLMs) such as GPT-4 have achieved exceptional
performance across various multi-modal tasks. However, the deployment of VLMs …