Search Results for author:
Found 7 papers, 5 papers with code
FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs
Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored.
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources.
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks.
Backdoor Defense via Adaptively Splitting Poisoned Dataset
With the split clean data pool and polluted data pool, ASD successfully defends against backdoor attacks during training.
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Existing attacks often insert some additional points into the point cloud as the trigger, or utilize a linear transformation (e. g., rotation) to construct the poisoned point cloud.
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications.
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
To this end, we propose the confusing perturbations-induced backdoor attack (CIBA).
