Related papers: HogVul: Black-box Adversarial Code Generation Fram…
Software vulnerabilities (SVs) pose a critical threat to safety-critical systems, driving the adoption of AI-based approaches such as machine learning and deep learning for software vulnerability detection. Despite promising results, most…
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input. We propose a…
Large Language Models (LLMs) have significantly aided developers by generating or assisting in code writing, enhancing productivity across various tasks. While identifying incorrect code is often straightforward, detecting vulnerabilities…
Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…
Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing failed adversarial perturbations reveals that the learned…
Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…
With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…
Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…
Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach…
In the realm of large vision-language models (LVLMs), adversarial jailbreak attacks serve as a red-teaming approach to identify safety vulnerabilities of these models and their associated defense mechanisms. However, we identify a critical…
Adversarial example generation becomes a viable method for evaluating the robustness of a machine learning model. In this paper, we consider hard-label black-box attacks (a.k.a. decision-based attacks), which is a challenging setting that…
Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adversarial examples is through a frequency-based approach.…
The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these…
Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…
With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving…
Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…
Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent…
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…
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…
Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have…