Related papers: Not All Prompts Are Secure: A Switchable Backdoor …
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…
Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…
Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few…
In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…
We propose a stealthy clean-label video backdoor attack against Deep Learning (DL)-based models aiming at detecting a particular class of spoofing attacks, namely video rebroadcast attacks. The injected backdoor does not affect spoofing…
Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…
The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…
Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether…
Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its…
Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…
The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…
The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…
In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…
Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or…