相关论文: Localization then Neutralization: Gradient-guided …

Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable to simple perturbations and adversarial attacks. To build an…

Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…

State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible…

While reasoning large language models (LLMs) demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where…

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than 100,000 LLM calls.…

The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their…

Adversarial attacks pose a severe security threat to the state-of-the-art speaker identification systems, thereby making it vital to propose countermeasures against them. Building on our previous work that used representation learning to…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

Stand-alone Visual Place Recognition (VPR) systems have little defence against a well-designed adversarial attack, which can lead to disastrous consequences when deployed for robot navigation. This paper extensively analyzes the effect of…

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect, multi-turn probing. To defend against this more nuanced form of deception, we present a…

Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. However, the performance of…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These…

Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim…

Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one. Existing methods mainly solve this task via a deep generative model, and focus on exploring the…

Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world imaging and vision applications, the associated safety…

Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training, which explicitly…

Gradient-based adversarial attacks subtly manipulate inputs of Machine Learning (ML) models to induce incorrect predictions. This paper investigates whether careful architectural choices alone can yield an inherently robust Deep Neural…

Malicious applications of visual manipulation have raised serious threats to the security and reputation of users in many fields. To alleviate these issues, adversarial noise-based defenses have been enthusiastically studied in recent…

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…