cyberintel.kalymoon.com · 6382 articles · updated every 4 hours · grows forever
arXiv:2608.02699v1 Announce Type: new Abstract: When algorithms make or influence consequential decisions---about loan eligibility, hiring, or healthcare---EU law grants affected individuals a Right t…
arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains …
arXiv:2608.02630v1 Announce Type: new Abstract: Knowledge graph engineering often distributes accepted state, observations, constraints, processes, and hypothetical scenarios across artifacts whose co…
arXiv:2608.02618v1 Announce Type: new Abstract: Recent studies have identified an ``Artificial Hivemind'' effect in Large Language Models (LLMs) causing models to converge on a narrow, homogenized con…
arXiv:2608.02606v1 Announce Type: new Abstract: Fault tolerance in classical computing has traditionally relied on static strategies like hardware redundancy and error-correcting codes. Biological sys…
arXiv:2608.02604v1 Announce Type: new Abstract: LLM-based agents are increasingly being deployed for data-related tasks, including data sense-making, exploration, and retrieval. However, their perform…
arXiv:2608.03130v1 Announce Type: new Abstract: Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attribute…
arXiv:2608.03110v1 Announce Type: new Abstract: Software-defined wide-area networking concentrates operational authority in controllers, orchestrators, and Internet-facing edges, but severity-only rem…
arXiv:2608.03096v1 Announce Type: new Abstract: Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks remai…
arXiv:2608.03093v1 Announce Type: new Abstract: Large language model (LLM) watermarking provides an important mechanism for tracing the provenance of generated text. Existing statistical watermarks ar…
arXiv:2608.03070v1 Announce Type: new Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much prote…
arXiv:2608.03009v1 Announce Type: new Abstract: Agentic artificial intelligence raises a new security concern: cyber threats that reason, act, and adapt locally without continuous human direction. We …
arXiv:2608.02995v1 Announce Type: new Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers…
arXiv:2608.02986v1 Announce Type: new Abstract: A software agent on a public blockchain accumulates authority and economic stakes, raising the engineering question of what makes it count as an individ…
arXiv:2608.02843v1 Announce Type: new Abstract: Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers mus…
arXiv:2608.02838v1 Announce Type: new Abstract: We study the verification of parameterised secrecy for cryptographic protocols in the Dolev-Yao model, where the number of protocol sessions is unbounde…
arXiv:2608.02821v1 Announce Type: new Abstract: Anomaly detectors are often the last line of defense for cyber-physical systems (CPS). But detectors built in very different ways, from deep neural netw…
arXiv:2608.02820v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace…
arXiv:2608.02806v1 Announce Type: new Abstract: By leveraging data from video-based perception systems, intelligent transportation systems (ITS) support safety-critical applications that improve road …
arXiv:2608.02774v1 Announce Type: new Abstract: AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive deta…
arXiv:2608.02698v1 Announce Type: new Abstract: Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastru…
arXiv:2608.02695v1 Announce Type: new Abstract: Software supply-chain attacks increasingly exploit an identity gap where compromised maintainer accounts authorize malicious changes. This work evaluate…
arXiv:2608.02687v1 Announce Type: new Abstract: AI coding agents accept free-form natural language prompts that may inadvertently contain credentials, personally identifiable information (PII), or pro…
arXiv:2608.02683v1 Announce Type: new Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex…