Latest news
-
AI Security via arXiv cs.CR
CAT-RAG: Improving Secure Code Generation with Category-Aware Agentic Retrieval
arXiv:2610.24907v1 Announce Type: new Abstract: Despite rapid progress in LLM-based code generation, security vulnerabilities remain widespread, and retrieval-augmented…
-
AI Security via arXiv cs.CR
Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
arXiv:2610.24916v1 Announce Type: new Abstract: Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and…
-
AI Security via arXiv cs.CR
SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
arXiv:2610.24999v1 Announce Type: new Abstract: Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field…
-
AI Security via arXiv cs.CR
Don't Judge an Agent by Its Messages: Private-State Leakage under Passive Monitoring of Agent Communication
arXiv:2610.25032v1 Announce Type: new Abstract: An AI agent can reproduce the distribution of its messages and of the receiver's task outcomes while disclosing private…
-
Vulnerabilities via arXiv cs.CR
Locate, Then Reason: End-to-End Patch Presence Testing in Stripped Binaries
arXiv:2610.25071v1 Announce Type: new Abstract: Binary patch presence testing (PPT) determines whether a security fix is present in a stripped binary. Prior systems…
-
AI Security via arXiv cs.CR
Towards End-to-End Privacy-Preserving AI for Real-Time ECG Monitoring
arXiv:2610.25094v1 Announce Type: new Abstract: Healthcare artificial intelligence is shifting from centralized archives toward distributed pipelines that combine…
-
AI Security via Help Net Security
Cloudflare bets you’re overpaying an LLM to read your invoices
Cloudflare released a preview of Clairic, an extraction model that pulls typed values out of messy text and images in one pass without generating tokens. In Cloudflare’s…
-
Vulnerabilities via Ubuntu Security
USN-8940-1: Perl XS::Parse::Keyword module vulnerability
It was discovered that the Perl XS::Parse::Keyword module did not correctly handle certain inputs. If a user or automated system were tricked into receiving specially…
- Advertisement
-
Breaches via Have I Been Pwned
Assurance Retraite - 70,372 breached accounts
In September 2024, the French national pension fund Assurance Retraite suffered a data breach affecting approximately 370k assistance beneficiaries. The data included…
-
Threat Intel via SANS Internet Storm Center
ISC Stormcast For Tuesday, October 20th, 2026 https://isc.sans.edu/podcastdetail/10142, (Tue, Oct 20th)
(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.
-
Ransomware via ransomware.live
🏴☠️ Payload has just published a new victim : BW Office World
BW Office World (bw-officeworld.de) is a German specialized online retailer providing comprehensive workspace and office supply solutions. Their catalog features office…
-
Ransomware via ransomware.live
🏴☠️ Payload has just published a new victim : Brüninghoff Group
Brüninghoff Group (brueninghoff.de) is a German construction and manufacturing company headquartered in Heiden, founded in 1974. The company specializes in turnkey…
-
Vulnerabilities via Datadog Security Labs
Introducing pathrunner: An AWS privilege escalation framework
Introducing pathrunner, a modular, cloud-native offensive security framework that automates the exploitation of AWS IAM privilege escalation paths.
-
AI Security via AI Incident Database
Homem usa IA para simular fotografia armado e ameaçar ex-companheira
Um caso inusitado de violência doméstica chamou a atenção das autoridades para o uso indevido de novas tecnologias em crimes de intimidação. Um homem foi preso pela…
-
Breaches via AI Incident Database
High Court Orders KBC to Delete Employees’ Biometric Data Over Privacy Breach
The High Court has ordered the Kenya Broadcasting Corporation (KBC) to delete and destroy biometric data collected from its employees after ruling that its facial…
-
AI Security via AI Incident Database
Kenya Union of Journalists v Kenya Broadcasting Corporation [2025] KEHC 17216 (KLR) - Judicial Review Miscellaneous Application E355 of 2025
Kenya Union of Journalists v Kenya Broadcasting Corporation \[2025] KEHC 17216 (KLR) - Judicial Review Miscellaneous Application E355 of 2025 REPUBLIC OF KENYA IN THE…
-
AI Security via AI Incident Database
AI system flaws push SHA into chaos, MPs say in explosive report
A parliamentary probe has unearthed how over-reliance on a faulty artificial intelligence system is allegedly causing widespread rejection of hospital claims at the…
-
AI Security via AI Incident Database
MPs flag systemic failures undermining Social Health Authority
Recurrent systemic failures, operational and policy gaps, and poor financial management are among the major threats to the effective implementation of the Social Health…
-
Breaches via AI Incident Database
MPs lay bare rot in SHA as Duale defends programme
MPs have exposed deep-rooted challenges hindering the delivery of health services under the new Social Health Authority. The revelations came as Health CS Aden Duale…
-
AI Security via AI Incident Database
Report on the Assessment of Social Health Authority (SHA) Utilization of Funds Disbursed Since Inception and Challenges Faced by Facilities
AIID editor's note: This is an abridged Markdown transcription of the supplied 55-page report, prepared to fit AIID's 50,000-character limit. It retains the cover text…