Related papers: Using Mechanistic Interpretability to Craft Advers…
Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities; however, these models remain highly susceptible to adversarial attacks. While existing research has explored white-box…
Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks,…
As Large Language Models (LLMs) are widely applied in various domains, the safety of LLMs is increasingly attracting attention to avoid their powerful capabilities being misused. Existing jailbreak methods create a forced…
Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other…
Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…
Deep learning (DL) architectures have been successfully used in many applications including wireless systems. However, they have been shown to be susceptible to adversarial attacks. We analyze DL-based models for a regression problem in the…
Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given…
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…
Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…
Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking…
To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…
The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and…
Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models…
Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious threat to deep learning-based systems compromising their…
Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…
Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improving alignment with user expectations.…
It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are…
Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…