相关论文: Erased but Exploitable: Black-box Embedding-Aware …

With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint framework in which we simultaneously probe and improve the…

Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input…

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or inducing…

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak…

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…

Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods…

Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…

Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time a model needs to be…

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor…

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To…

In this paper, we investigate the impact of adversarial attacks on the explainability of deep learning models, which are commonly criticized for their black-box nature despite their capacity for autonomous feature extraction. This black-box…

White-box Adversarial Example (AE) attacks towards Deep Neural Networks (DNNs) have a more powerful destructive capacity than black-box AE attacks in the fields of AE strategies. However, almost all the white-box approaches lack…

Recent advances in text-to-image generative models have raised concerns about their potential to produce harmful content when provided with malicious input text prompts. To address this issue, two main approaches have emerged: (1)…

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and…

Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering content via text prompts. However, many undesired outputs, such as…