Related papers: A Large Language Model Approach to Generating Bypa…

Generating thorough natural language explanations for threat detections remains an open problem in cybersecurity research, despite significant advances in automated malware detection systems. In this work, we present AutoMalDesc, an…

As the smartphone market leader, Android has been a prominent target for malware attacks. The number of malicious applications (apps) identified for it has increased continually over the past decade, creating an immense challenge for all…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with…

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Large language models (LLMs) are becoming more advanced and widespread and have shown their applicability to various domains, including cybersecurity. Static malware analysis is one of the most important tasks in cybersecurity; however, it…

Malware authors often employ code obfuscations to make their malware harder to detect. Existing tools for generating obfuscated code often require access to the original source code (e.g., C++ or Java), and adding new obfuscations is a…

Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based detection. Integrating generative AI into offensive toolchains enables attackers to synthesize…

Machine Learning (ML) promises to enhance the efficacy of Android Malware Detection (AMD); however, ML models are vulnerable to realistic evasion attacks--crafting realizable Adversarial Examples (AEs) that satisfy Android malware domain…

The tremendous growth in smart devices has uplifted several security threats. One of the most prominent threats is malicious software also known as malware. Malware has the capability of corrupting a device and collapsing an entire network.…

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify…

The problem of data contamination is now almost inevitable during the development of large language models (LLMs), with the training data commonly integrating those evaluation benchmarks even unintentionally. This problem subsequently makes…