cyberintel.kalymoon.com · 29836 articles · updated every 4 hours · grows forever
arXiv:2605.24903v1 Announce Type: new Abstract: Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on fully…
arXiv:2605.24834v1 Announce Type: new Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversaria…
arXiv:2605.24817v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become an increasingly important paradigm for scaling Large Language Models (LLMs). As MoE models are increa…
arXiv:2605.24765v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to cybersecurity question answering (QA) for critical tasks such as incident response and vulnerab…
arXiv:2605.24696v1 Announce Type: new Abstract: Streaming network intrusion detection systems must process flows continuously while keeping memory bounded, but most current methods leave alerting thre…
arXiv:2605.24663v1 Announce Type: new Abstract: This paper presents CyBOKClaw, an interpretable human-in-the-loop retrieval framework for mapping cybersecurity keywords or phrases (KWoPs) to the Cyber…
arXiv:2605.24632v1 Announce Type: new Abstract: Recent demonstrations of large language models producing candidate and confirmed vulnerabilities in production software have renewed the narrative that …
arXiv:2605.24559v1 Announce Type: new Abstract: Ransomware has grown to become one of the most damaging types of cybercrime, affecting private and public organizations in any sector. While early types…
arXiv:2605.24552v1 Announce Type: new Abstract: Representation engineering (RepE) defenses have shown strong robustness against jailbreak attacks on large language models (LLMs). However, these method…
arXiv:2605.24551v1 Announce Type: new Abstract: Cybersecurity awareness training has historically adopted a one-size-fits-all approach, despite established individual differences in how users process …
arXiv:2605.24542v1 Announce Type: new Abstract: This paper examines the erosion of Public Key Cryptography (PKC) security under adaptive adversarial optimisation driven by artificial intelligence. The…
arXiv:2605.24535v1 Announce Type: new Abstract: Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions …
arXiv:2605.24421v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to …
arXiv:2605.24312v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has become central to large language model (LLM) deployments, grounding responses in enterprise or proprietary data…
arXiv:2605.24309v1 Announce Type: new Abstract: We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position,…
arXiv:2605.24300v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for code generation, but their security reliability remains inconsistent across languages and prompting str…
arXiv:2605.24298v1 Announce Type: new Abstract: The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of sec…
arXiv:2605.24294v1 Announce Type: new Abstract: Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propose …
arXiv:2605.24248v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a hos…
arXiv:2605.24245v1 Announce Type: new Abstract: Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in order to produce str…
arXiv:2605.24239v1 Announce Type: new Abstract: Many existing Artificial Intelligence (AI) solutions on mobile devices rely on an extensive collection of sensitive data, raising privacy concerns and o…
arXiv:2605.24206v1 Announce Type: new Abstract: Along with the recent rise in popularity of Electric Vehicles (EVs), Electric Vehicle Supply Equipment (EVSE) has emerged as a new target for cyber atta…
arXiv:2605.24190v1 Announce Type: new Abstract: Electric Vehicles (EVs) have emerged as significant disruptors in the transportation sector over the past decade. Their growing popularity and adoption …
arXiv:2605.24069v1 Announce Type: new Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented au…