cyberintel.kalymoon.com · 41004 articles · updated every 4 hours · grows forever
arXiv:2605.08399v1 Announce Type: new Abstract: Tool-augmented language models can extend small language models with external executable skills, but scaling the tool library creates a coupled challeng…
arXiv:2605.08388v1 Announce Type: new Abstract: Human-AI teams play a pivotal role in improving overall system performance when neither the human nor the model can achieve such performance on their ow…
arXiv:2605.08386v1 Announce Type: new Abstract: Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills…
arXiv:2605.08374v1 Announce Type: new Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval…
arXiv:2605.08368v1 Announce Type: new Abstract: Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But…
arXiv:2605.08360v1 Announce Type: new Abstract: Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed se…
arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human…
arXiv:2605.08220v1 Announce Type: new Abstract: The automated extraction of data from scientific charts is a critical task for large-scale literature analysis. While multimodal Large Language Models (…
arXiv:2605.08200v1 Announce Type: new Abstract: A pervasive intuition holds that vision-language models (VLMs) are most trustworthy when their attention maps look sharp: concentrated attention on the …
arXiv:2605.09232v1 Announce Type: new Abstract: The increasing deployment of Internet-of-Things (IoT) devices has accelerated the use of distributed learning frameworks, where data remains local while…
arXiv:2605.09225v1 Announce Type: new Abstract: Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat,…
arXiv:2605.09203v1 Announce Type: new Abstract: Watermarks for AI-generated images are meant to support downstream decisions about provenance, manipulation, and trust. In the settings that motivate wa…
arXiv:2605.09124v1 Announce Type: new Abstract: Smart contract security has progressed from vulnerability detection toward a broader research agenda that includes semantic reasoning, automated repair,…
arXiv:2605.09115v1 Announce Type: new Abstract: Modern security environments generate fragmented signals across cloud resources, identities, configurations, and third-party security tools. Although AI…
arXiv:2605.09070v1 Announce Type: new Abstract: Many jailbreak attack research papers report attack success rates for a limited number of parameter settings, even though there are many combinations of…
arXiv:2605.09033v1 Announce Type: new Abstract: Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new po…
arXiv:2605.08984v1 Announce Type: new Abstract: As Field-Programmable Gate Arrays (FPGAs) scale in multi-tenant cloud and edge-AI environments, the configuration bitstream has become a critical, yet o…
arXiv:2605.08922v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed on blockchain platforms, yet the design space that governs their interaction remains poorly understood. T…
arXiv:2605.08910v1 Announce Type: new Abstract: The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection …
arXiv:2605.08878v1 Announce Type: new Abstract: Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representati…
arXiv:2605.08763v1 Announce Type: new Abstract: Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets…
arXiv:2605.08690v1 Announce Type: new Abstract: Modern cryptography is hinged on "not learning from mistakes": trying numerous wrong keys, should not help one identify the right key. Indeed, it worked…
arXiv:2605.08604v1 Announce Type: new Abstract: Embedded and Internet-of-Things (IoT) devices play a critical role in modern life. Their software and firmware, often developed in memory-unsafe languag…
arXiv:2605.08586v1 Announce Type: new Abstract: This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name …