While existing backdoor attacks have successfully infected multimodal contrastive learning
models such as CLIP they can be easily countered by specialized backdoor defenses for …

Abstract Model quantization is widely used to compress and accelerate deep neural
networks. However recent studies have revealed the feasibility of weaponizing model …

Image generation techniques have been gaining increasing attention recently, but concerns
have been raised about the potential misuse and intellectual property (IP) infringement …

Federated graph learning (FedGL) is an emerging federated learning (FL) framework that
extends FL to learn graph data from diverse sources without accessing the data. FL for non …

Object detection models are vulnerable to backdoor or trojan attacks, where an attacker can
inject malicious triggers into the model, leading to altered behavior during inference. As a …

Instruction Fine-Tuning (IFT) has become an essential method for adapting base Large
Language Models (LLMs) into variants for professional and private use. However …

Pre-trained large models for multimodal contrastive learning, such as CLIP, have been
widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks …

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-
training dataset which consists of images or image-text pairs. CL is vulnerable to data …

Pre-trained models (PTMs) are extensively utilized in various downstream tasks. Adopting
untrusted PTMs may suffer from backdoor attacks, where the adversary can compromise the …

Recent studies have revealed that GNNs are highly susceptible to multiple adversarial
attacks. Among these, graph backdoor attacks pose one of the most prominent threats …