Related papers: Toward Polymorphic Backdoor against Semantic Commu…
Recently, backdoor attacks have become an emerging threat to the security of machine learning models. From the adversary's perspective, the implanted backdoors should be resistant to defensive algorithms, but some recently proposed…
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…
Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…
This paper investigates the secure resource allocation for a downlink integrated sensing and communication system with multiple legal users and potential eavesdroppers. In the considered model, the base station (BS) simultaneously transmits…
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 are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…
Semantic communication (SemCom) has the potential to significantly reduce communication delay in vehicle-to-everything (V2X) communications within vehicular networks (VNs). However, the deployment of vehicular SemCom networks…
Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…
Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…
Graph convolutional networks (GCNs) have been very effective in addressing the issue of various graph-structured related tasks. However, recent research has shown that GCNs are vulnerable to a new type of threat called a backdoor attack,…
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…
Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned…
Backdoor attacks are rapidly emerging threats to deep neural networks (DNNs). In the backdoor attack scenario, attackers usually implant the backdoor into the target model by manipulating the training dataset or training process. Then, the…
The side-channel attack is an attack method based on the information gained about implementations of computer systems, rather than weaknesses in algorithms. Information about system characteristics such as power consumption, electromagnetic…
Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…
Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…
Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor attacks on code models face a fundamental trade-off between transferability and…
Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…
Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…