相关论文: A Chaos Driven Metric for Backdoor Attack Detectio…

Threat modeling is a popular method to securely develop systems by achieving awareness of potential areas of future damage caused by adversaries. However, threat modeling for systems relying on Artificial Intelligence is still not well…

Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen…

Network intrusion detection systems (NIDSs) play an important role in computer network security. There are several detection mechanisms where anomaly-based automated detection outperforms others significantly. Amid the sophistication and…

Poisoning attacks are a category of adversarial machine learning threats in which an adversary attempts to subvert the outcome of the machine learning systems by injecting crafted data into training data set, thus increasing the machine…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a…

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent…

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…

Network Intrusion Detection System (NIDS) is an essential tool in securing cyberspace from a variety of security risks and unknown cyberattacks. A number of solutions have been implemented for Machine Learning (ML), and Deep Learning (DL)…

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the…

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

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 are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and derive principled…

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A…