cyberintel.kalymoon.com · 47042 articles · updated every 4 hours · grows forever
arXiv:2410.13900v3 Announce Type: replace Abstract: The scrutiny surrounding vote-by-mail (VBM) in the United States has increased in recent years, highlighting the need for a rigorous quantitative fr…
arXiv:2410.13891v3 Announce Type: replace Abstract: Transferable Targeted Attacks (TTAs) face significant challenges due to severe overfitting to surrogate models. Recent breakthroughs heavily rely on…
arXiv:2406.06958v2 Announce Type: replace Abstract: Online advertising relies on a complex and opaque supply chain that involves multiple stakeholders, including advertisers, publishers, and ad-networ…
arXiv:2604.03199v1 Announce Type: cross Abstract: All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibra…
arXiv:2604.02617v1 Announce Type: cross Abstract: Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing ap…
arXiv:2604.02457v1 Announce Type: cross Abstract: Automatic license plate reader (ALPR) systems are widely deployed to identify and track vehicles. While prior work has demonstrated vulnerabilities in…
arXiv:2604.02366v1 Announce Type: cross Abstract: In a companion paper, we prove that the Burau-Lyapunov exponent LE discriminates focused from dispersed privilege escalation ratchets in cloud IAM gra…
arXiv:2604.03205v1 Announce Type: new Abstract: The rapid adoption of the Internet of Medical Things (IoMT) is transforming healthcare by enabling seamless connectivity among medical devices, systems,…
arXiv:2604.03131v1 Announce Type: new Abstract: Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be…
arXiv:2604.03121v1 Announce Type: new Abstract: Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying sa…
arXiv:2604.03104v1 Announce Type: new Abstract: Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approaches lack the semantic depth required for pat…
arXiv:2604.03081v1 Announce Type: new Abstract: LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. …
arXiv:2604.03070v1 Announce Type: new Abstract: Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments, making leakage risks …
arXiv:2604.03043v1 Announce Type: new Abstract: In a healthcare environment, the healthcare interoperability platforms based on HL7 FHIR allow concurrent, asynchronous access to a set of shared patien…
arXiv:2604.02837v1 Announce Type: new Abstract: Agent Skills is an emerging open standard that defines a modular, filesystem-based packaging format enabling LLM-based agents to acquire domain-specific…
arXiv:2604.02774v1 Announce Type: new Abstract: Providing reliable, affordable, and secure Internet connectivity in rural areas remains a major challenge. Pay-for-use Wi-Fi hotspots are emerging as a …
arXiv:2604.02771v1 Announce Type: new Abstract: Smart contracts are increasingly targeted by adversaries employing obfuscation techniques such as bogus code injection and control flow manipulation to …
arXiv:2604.02767v1 Announce Type: new Abstract: When Agent A delegates to Agent B, which invokes Tool C on behalf of User X, no existing framework can answer: whose authorization chain led to this act…
arXiv:2604.02623v1 Announce Type: new Abstract: Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertentl…
arXiv:2604.02591v1 Announce Type: new Abstract: As quantum computing matures toward the realization of Cryptographically Relevant Quantum Computers (CRQC), global cryptographic infrastructure faces an…
arXiv:2604.02574v1 Announce Type: new Abstract: Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the …
arXiv:2604.02548v1 Announce Type: new Abstract: The increasing complexity and volume of software systems have heightened the importance of identifying and mitigating security vulnerabilities. The exis…
arXiv:2604.02522v1 Announce Type: new Abstract: Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trus…
arXiv:2604.02490v1 Announce Type: new Abstract: Malware family classification remains a challenging task in automated malware analysis, particularly in real-world settings characterized by obfuscation…