相关论文: TextGuard: Provable Defense against Backdoor Attac…

Trojan backdoor is a poisoning attack against Neural Network (NN) classifiers in which adversaries try to exploit the (highly desirable) model reuse property to implant Trojans into model parameters for backdoor breaches through a poisoned…

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released language models. As a countermeasure, backdoor detection methods…

As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Recently, the new ciphertext side channels resulting from the deterministic memory encryption in Trusted Execution Environments (TEEs), enable ciphertexts to manifest identifiable patterns when being sequentially written to the same memory…

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

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,…

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright…

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…