Latest news
-
AI Security via arXiv cs.CR
NetAgent: Multi-Task Agentic Network Traffic Analysis Made Practical
arXiv:2610.07386v1 Announce Type: new Abstract: Network traffic analysis is central to network security, spanning tasks from intrusion detection to encrypted traffic…
-
AI Security via arXiv cs.CR
Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security
arXiv:2610.07489v1 Announce Type: new Abstract: Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicular…
-
AI Security via arXiv cs.CR
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
arXiv:2610.07510v1 Announce Type: new Abstract: Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain…
-
Threat Intel via arXiv cs.CR
BVI: Lightweight, Data-Centric Blockchain-Based Verification of Identity Claims
arXiv:2610.07531v1 Announce Type: new Abstract: A person who answers an unexpected call claiming to come from a bank has no way to check the claim. Australian text…
-
AI Security via arXiv cs.CR
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
arXiv:2610.07532v1 Announce Type: new Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect…
-
Threat Intel via arXiv cs.CR
CISB-Bench: An Auditable Source--IR Dataset of Compiler-Introduced Security Bugs
arXiv:2610.07635v1 Announce Type: new Abstract: Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a…
-
AI Security via arXiv cs.CR
HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?
arXiv:2610.07639v1 Announce Type: new Abstract: Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain…
-
AI Security via arXiv cs.CR
SkillPoison: Progressive Skill Poisoning via Successful Experiences
arXiv:2610.07645v1 Announce Type: new Abstract: Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill…
- Advertisement
-
Breaches via arXiv cs.CR
PerSpectron: Detecting Invariant Footprints of Microarchitectural Attacks with Perceptron
arXiv:2610.07691v1 Announce Type: new Abstract: Detecting microarchitectural attacks is critical given their proliferation in recent years. Many of these attacks exhibit…
-
Threat Intel via arXiv cs.CR
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
arXiv:2610.07723v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are…
-
Threat Intel via arXiv cs.CR
What Response Marginals Miss: Adaptive Query Complexity of Functional Backdoor Recovery
arXiv:2610.07771v1 Announce Type: new Abstract: Functional backdoor recovery finds any trigger whose attack success rate is at least a given threshold rather than to…
-
AI Security via arXiv cs.CR
SCSM: A Traffic-Native Foundation Model for Transferable Website Fingerprinting
arXiv:2610.07776v1 Announce Type: new Abstract: Website fingerprinting infers the websites visited by users from encrypted traffic metadata. However, models trained…
-
Vulnerabilities via Help Net Security
Check your X.Org server version because a dozen vulnerabilities have been patched
X.Org fixed 12 security flaws in the X server and Xwayland, with the repairs shipping in xorg-server 21.1.25 and xwayland-24.1.14. Nine of the flaws can lead to…
-
Breaches via Have I Been Pwned
Angel One - 6,765,054 breached accounts
In July 2024, the Indian stock brokerage firm Angel One confirmed that data leaked online related to a breach that occurred in April 2023. The leaked data included 7.9M…
-
Threat Intel via SANS Internet Storm Center
ISC Stormcast For Wednesday, October 7th, 2026 https://isc.sans.edu/podcastdetail/10126, (Wed, Oct 7th)
(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.
-
Breaches via SecurityWeek
Personal Information for Over 1 Million People Stolen in a Cyberattack on Arizona’s Court System
The Arizona Supreme Court said the information was copied for people dating back as far as 30 years.
-
Vulnerabilities via Chrome Releases
Long Term Support (LTS) channel for ChromeOS - Major update from 144-> 150
The Long Term Support Candidate LTC-150 has been promoted to ChromeOS LTS-150 and is rolling out to most ChromeOS devices. The current version is 150.0.7871.256…
-
Vulnerabilities via ransomware.live
🏴☠️ Termite has just published a new victim : Aon
Aon plc is an international professional services firm. It has two divisions: Risk Capital, which provides brokerage and consulting services for risk management…
-
AI Security via Simon Willison
OpenAI “rogue” agent activities found on Wikimedia projects
OpenAI “rogue” agent activities found on Wikimedia projects Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found…
-
Vulnerabilities via Splunk
SVD-2026-1005: Third-Party Package Updates in Splunk Add-on for Amazon Web Services - September 2026
Splunk remedied common vulnerabilities and exposures (CVEs) in third-party packages in Splunk Add-on for Amazon Web Services version 8.2.2 and higher.