cyberintel.kalymoon.com · 40251 articles · updated every 4 hours · grows forever
arXiv:2605.13100v1 Announce Type: new Abstract: Security often receives insufficient developer attention because it does not directly generate visible value, leading to underinvestment in practice. We…
arXiv:2605.13095v1 Announce Type: new Abstract: Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models, yet is typically evaluated only under adversari…
arXiv:2605.13044v1 Announce Type: new Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but…
arXiv:2605.12990v1 Announce Type: new Abstract: In the official whitepaper of Secure Encrypted Virtualization with Secure Nested Paging (SEV-SNP), AMD explicitly emphasizes the capability to prevent T…
arXiv:2605.12976v1 Announce Type: new Abstract: Modern cloud-native environments present a fundamentally different exfiltration threat surface than traditional file-based scenarios. Attackers targetin…
arXiv:2605.12942v1 Announce Type: new Abstract: Large-scale datasets have been a key driving force behind the rapid progress of deep learning, but their storage, computational, and energy costs have b…
arXiv:2605.12927v1 Announce Type: new Abstract: Standalone virtual reality (VR) headsets process highly sensitive personal, professional, and health-related data, yet their susceptibility to non-conta…
arXiv:2605.12875v1 Announce Type: new Abstract: Programmatic skills in LLM ecosystems consist of a natural-language description and executable implementation files. Users and LLMs rely on the descript…
arXiv:2605.12869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circ…
arXiv:2605.12841v1 Announce Type: new Abstract: Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical …
arXiv:2605.12827v1 Announce Type: new Abstract: Graph neural networks (GNNs) deployed as cloud services can be \emph{stolen} through \emph{model-extraction attacks}, which train a surrogate from query…
arXiv:2605.12746v1 Announce Type: new Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code gen…
arXiv:2605.12743v1 Announce Type: new Abstract: Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or tra…
arXiv:2605.12565v1 Announce Type: new Abstract: Existing automated red-teaming pipelines often miss attacks that depend on attacker identity, framing, or multi-turn tactics. This under-coverage undere…
arXiv:2605.12563v1 Announce Type: new Abstract: Script-language runtimes such as Python, Lua, and JavaScript are widely deployed in security sensitive contexts, yet they remain difficult to test becau…
arXiv:2605.12535v1 Announce Type: new Abstract: LM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting.…
arXiv:2605.12529v1 Announce Type: new Abstract: In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model edi…
A vulnerability identified as problematic has been detected in shellhub-io shellhub up to 0.24.1 . Affected by this issue is some unknown functionality of the file /api/devices/ . Performing a manipul…
A vulnerability labeled as problematic has been found in shellhub-io shellhub up to 0.24.1 . This affects an unknown part of the file /api/namespaces/:tenant . Executing a manipulation can lead to aut…
A vulnerability marked as critical has been reported in CubeCart up to 6.6.x . This vulnerability affects unknown code of the file /api/v1/files . The manipulation leads to unrestricted upload. This v…
A vulnerability described as critical has been identified in CubeCart up to 6.6.x . This issue affects the function sqlSafe of the file admin.php?_g=orders&node=transactions of the component Admin Pas…
A vulnerability classified as critical has been found in CubeCart up to 6.7.1 . Impacted is the function User::passwordRequest of the file /index.php?_a=recover of the component Request Header Handler…
A vulnerability classified as critical was found in CubeCart up to 6.7.2 . The affected element is an unknown function of the file files/print..php . Such manipulation leads to code injection. This vu…
A vulnerability, which was classified as critical , has been found in CKAN up to 2.10.9/2.11.4 . The impacted element is the function datastore_search_sql . Performing a manipulation results in sql in…