Related papers: ShellForge: Adversarial Co-Evolution of Webshell G…

Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, which fundamentally limit robustness, particularly in multimodal…

Federated learning (FL) allows participants to jointly train a machine learning model without sharing their private data with others. However, FL is vulnerable to poisoning attacks such as backdoor attacks. Consequently, a variety of…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Web application firewall (WAF) examines malicious traffic to and from a web application via a set of security rules. It plays a significant role in securing Web applications against web attacks. However, as web attacks grow in…

Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…

Automated detection of vulnerabilities in source code is an essential cybersecurity challenge, underpinning trust in digital systems and services. Graph Neural Networks (GNNs) have emerged as a promising approach as they can learn…

Deep neural networks (DNNs) are inherently vulnerable to adversarial inputs: such maliciously crafted samples trigger DNNs to misbehave, leading to detrimental consequences for DNN-powered systems. The fundamental challenges of mitigating…

Federated learning enables learning from decentralized data sources without compromising privacy, which makes it a crucial technique. However, it is vulnerable to model poisoning attacks, where malicious clients interfere with the training…

Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existing vulnerability detection methods mostly rely on…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Evasion techniques allow malicious code to never be observed. This impacts significantly the detection capabilities of tools that rely on either dynamic or static analysis, as they never get to process the malicious code. The dynamic nature…

The rapid progress in deep generative models has led to the creation of incredibly realistic synthetic images that are becoming increasingly difficult to distinguish from real-world data. The widespread use of Variational Models, Diffusion…

Adversarial EXEmples are carefully-perturbed programs tailored to evade machine learning Windows malware detectors, with an ongoing effort to develop robust models able to address detection effectiveness. However, even if robust models can…

Federated learning (FL) is a popular privacy-preserving edge-to-cloud technique used for training and deploying artificial intelligence (AI) models on edge devices. FL aims to secure local client data while also collaboratively training a…

Recent studies have shown that federated learning (FL) is vulnerable to poisoning attacks that inject a backdoor into the global model. These attacks are effective even when performed by a single client, and undetectable by most existing…

The drastic increase of JavaScript exploitation attacks has led to a strong interest in developing techniques to enable malicious JavaScript analysis. Existing analysis tech- niques fall into two general categories: static analysis and…

Website fingerprinting attacks enable an adversary to infer which website a victim is visiting, even if the victim uses an encrypting proxy, such as Tor. Previous work has shown that all proposed defenses against website fingerprinting…

Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…

Since the introduction of bcrypt in 1999, adaptive password hashing functions, whereby brute-force resistance increases symmetrically with computational difficulty for legitimate users, have been our most powerful post-breach countermeasure…

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…