Related papers: ATGen: Adversarial Reinforcement Learning for Test…

As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models (LLMs) offer significant potential in cybersecurity due to their advanced capabilities in text processing and…

The proliferation of Large Language Models (LLMs), such as ChatGPT, has raised concerns about their potential impact on academic integrity, prompting the need for LLM-resistant exam designs. This article investigates the performance of LLMs…

Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Augmenting toxic language data in a controllable and class-specific manner is crucial for improving robustness in toxicity classification, yet remains challenging due to limited supervision and distributional skew. We propose ToxiGAN, a…

We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…

Large Language Models (LLMs) have recently achieved strong performance in software code generation. However, applying them to hardware description languages (HDLs), such as Verilog, remains challenging because high-quality training data are…

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…

Automatic code synthesis from natural language descriptions is a challenging task. We witness massive progress in developing code generation systems for domain-specific languages (DSLs) employing sequence-to-sequence deep learning…

Machine learning has proven to be a useful tool for automated malware detection, but machine learning models have also been shown to be vulnerable to adversarial attacks. This article addresses the problem of generating adversarial malware…

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still…

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, this paradigm is…

This study examined code issue detection and revision automation by integrating Large Language Models (LLMs) such as OpenAI's GPT-3.5 Turbo and GPT-4o into software development workflows. A static code analysis framework detects issues such…

Large Language Models (LLMs) can generate plausible test code. Intuitively they generate this by imitating tests seen in their training data, rather than reasoning about execution semantics. However, such reasoning is important when…

The rapid advancement of domain-specific large language models (LLMs) in fields like law necessitates frameworks that account for nuanced regional legal distinctions, which are critical for ensuring compliance and trustworthiness. Existing…

Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, their robustness under adversarial conditions remains…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and incorrect results. Current libraries for structured LLM…

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic,…