Related papers: SecureCode: A Production-Grade Multi-Turn Dataset …
We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCode trains a reasoning model in two stages: (i) Rule…
LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a…
To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human values. This dataset encompasses human preferences in…
Large Language Models (LLMs) have transformed software development by enabling code generation, automated debugging, and complex reasoning. However, their continued advancement is constrained by the scarcity of high-quality, publicly…
Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting strategies. Existing prompt engineering improves functional correctness but rarely ensures…
Lack of security expertise among software practitioners is a problem with many implications. First, there is a deficit of security professionals to meet current needs. Additionally, even practitioners who do not plan to work in security may…
The growing complexity of cyber threats and the limitations of traditional vulnerability detection tools necessitate novel approaches for securing software systems. We introduce MalCodeAI, a language-agnostic, multi-stage AI pipeline for…
Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work,…
The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion detection systems. This work presents SecureScan, an AI-driven, triple-layer detection framework…
Advanced AI systems offer substantial benefits but also introduce risks. In 2025, AI-enabled cyber offense has emerged as a concrete example. This technical report applies a quantitative risk modeling methodology (described in full in a…
We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds.…
The rapid advancement of AI has enabled highly realistic speech synthesis and voice cloning, posing serious risks to voice authentication, smart assistants, and telecom security. While most prior work frames spoof detection as a binary…
Automation of code reviews using AI models has garnered substantial attention in the software engineering community as a strategy to reduce the cost and effort associated with traditional peer review processes. These models are typically…
The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of…
The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded risks underexplored. In this work, we investigate LLM safety in the context of the Thai…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
Sonatype's 2023 report found that 97% of developers and security leads integrate generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their development process. Concerns about the security implications of…
This paper provides a comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs). We explore LLM applications across various domains, including hardware design security, intrusion detection,…
The increasing reliance on web services has led to a rise in cybersecurity threats, particularly Cross-Site Scripting (XSS) attacks, which target client-side layers of web applications by injecting malicious scripts. Traditional Web…
The increasing use of Large Language Models (LLMs) in agentic applications highlights the need for robust safety guard models. While content safety in English is well-studied, non-English languages lack similar advancements due to the high…