Latest news
-
AI Security via arXiv cs.CR
What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains
arXiv:2610.19498v1 Announce Type: new Abstract: Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q…
-
Vulnerabilities via arXiv cs.CR
Mission (Im)Possible: Towards Autonomous Discovery of Autopilot Logic Flaws in Open-Source Drone Frameworks
arXiv:2610.19566v1 Announce Type: new Abstract: Autonomous drones are increasingly deployed in safety-critical tasks, yet their autopilot software can still contain…
-
Threat Intel via arXiv cs.CR
A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference
arXiv:2610.19607v1 Announce Type: new Abstract: Rising privacy concerns around large language models have accelerated research in private Transformer inference (PTI)…
-
AI Security via arXiv cs.CR
AWARE-RG: Abstraction Aware Explanation of Resiliency Graphs for Cyber Physical Systems
arXiv:2610.19650v1 Announce Type: new Abstract: Understanding the security posture of cyber physical systems (CPS) requires reasoning across both information technology…
-
AI Security via arXiv cs.CR
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
arXiv:2610.19766v1 Announce Type: new Abstract: Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational…
-
Vulnerabilities via arXiv cs.CR
Adaptive and Proximal Federated Optimization for Transferable Network Intrusion Detection
arXiv:2610.19808v1 Announce Type: new Abstract: Network Intrusion Detection Systems (NIDS) based on deep learning often fail to detect attack classes that are absent…
-
AI Security via arXiv cs.CR
DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates
arXiv:2610.19830v1 Announce Type: new Abstract: Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach…
-
AI Security via arXiv cs.CR
Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?
arXiv:2610.19856v1 Announce Type: new Abstract: Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making…
- Advertisement
-
Threat Intel via arXiv cs.CR
Bilinear Compressive Security with Finitely Many Samples
arXiv:2610.19898v1 Announce Type: new Abstract: Bilinear Compressive Security (BCS) is a lightweight encryption scheme that combines compressed sensing with a fresh…
-
Threat Intel via arXiv cs.CR
Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness
arXiv:2610.19947v1 Announce Type: new Abstract: Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their…
-
AI Security via arXiv cs.CR
Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks
arXiv:2610.19971v1 Announce Type: new Abstract: Automated jailbreak attacks rely on evaluation feedback to optimize adversarial prompts, but existing methods often lack…
-
AI Security via arXiv cs.CR
ESAU: Expeditious Swarm Remote Attestation for Pub-Sub IoT Networks with Untrusted Cloud-based Proxy Verifier
arXiv:2610.20047v1 Announce Type: new Abstract: As Internet of Things (IoT) devices collect and process data, security is essential. IoT devices often combine with other…
-
AI Security via arXiv cs.CR
CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
arXiv:2610.20049v1 Announce Type: new Abstract: Agents extend their capabilities through reusable skills that package instructions, executable code, and resources…
-
Threat Intel via arXiv cs.CR
FreeSBee: A Constant-Time Compilation Pipeline
arXiv:2610.20171v1 Announce Type: new Abstract: Constant-time execution is an important security property, especially for IoT devices, that prevents the leakage of…
-
Threat Intel via arXiv cs.CR
Secret Sharing from Non-Extractable Randomness
arXiv:2610.20173v1 Announce Type: new Abstract: Bosley and Dodis (TCC 2007) proved that a class of imperfect randomness sources that suffices for information-theoretic…
-
Vulnerabilities via arXiv cs.CR
P2Patch: Exploit-Guided Vulnerability Repair
arXiv:2610.20245v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for automated program repair, patching software…
-
Breaches via ransomware.live
🏴☠️ N0n has just published a new victim : Company #68
manufacturing · USA | [PENDING EXPOSURE]
-
Threat Intel via SANS Internet Storm Center
ISC Stormcast For Thursday, October 15th, 2026 https://isc.sans.edu/podcastdetail/10138, (Thu, Oct 15th)
(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.
-
Breaches via ransomware.live
🏴☠️ N0n has just published a new victim : Company #67
FX liquidity and trading technology · Netherlands | [PENDING EXPOSURE]
-
Breaches via ransomware.live
🏴☠️ N0n has just published a new victim : Company #66
software quality assurance (Wolters Kluwer/CCH Axcess test l · California, USA | [PENDING EXPOSURE]