Related papers: The Compliance Paradox: Semantic-Instruction Decou…

In Computer Science (CS) education, understanding factors contributing to students' programming difficulties is crucial for effective learning support. By identifying specific issues students face, educators can provide targeted assistance…

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While…

The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis (SCA) tools struggle to…

Large Language Models (LLMs) challenge conventional automated programming assessment because students can now produce functionally correct code without demonstrating corresponding understanding. This paper makes two contributions. First, it…

The integration of Large Language Models (LLMs) into the software development lifecycle (SDLC) masks a critical socio-technical failure: Cognitive-Systemic Collapse. This paper introduces "Epistemological Debt," the hidden carrying cost…

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting…

Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed. However, we reveal a counterintuitive phenomenon: instruction following can…

This paper presents a conceptual and methodological framework for large language model (LLM) based student simulation in educational settings. The authors identify a core failure mode, termed the "competence paradox" in which broadly…

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

Large Language Models (LLMs) have shown promising performance in software vulnerability detection, particularly after domain-specific Supervised Fine-Tuning (SFT). However, it remains unclear whether these models genuinely internalize…

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

Large language model (LLM) leaderboards rank AI models using standardized benchmarks and have become highly visible across computer science, despite known limitations in their reliability and robustness. Yet how they shape researchers'…

Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabilities is the lack of an instruction hierarchy. Modern LLM…