SIG-1161
- AI security
When AI Finds Hidden Messages, Does It Report?
arXiv:2610.10620v1 Announce Type: new Abstract: When an assistant encounters a message for another AI, does it tell its…
via arXiv cs.CROpen
AI Security
No signal on this page matches that topic.
SIG-1162
- LLMs
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
arXiv:2610.10625v1 Announce Type: new Abstract: Looped Language Models (LoopLMs) provide a parameter efficient approach…
via arXiv cs.CROpen
SIG-1163
- Policy & governance
DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits
arXiv:2610.10735v1 Announce Type: new Abstract: Pre-trained models (PTMs) are widely distributed as serialized…
via arXiv cs.CROpen
SIG-1164
- Prompt injection
- Defence & detection
BRANCH: Bypassing Multi-Scanner AI Guardrails
arXiv:2610.10742v1 Announce Type: new Abstract: AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks…
via arXiv cs.CROpen
SIG-1165
- Deepfakes
- Model attacks
Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection
arXiv:2610.10752v1 Announce Type: new Abstract: Audio deepfake detectors remain vulnerable to adversarial perturbations…
via arXiv cs.CROpen
SIG-1166
- Model attacks
- Privacy & data
Power Side-Channel Membership Inference Attack on Embedded Machine Learning
arXiv:2610.10909v1 Announce Type: new Abstract: Membership inference attacks (MIAs) threaten the privacy of machine…
via arXiv cs.CROpen
SIG-1167
- LLMs
Speedbumps: Rejection Attacks on Speculative Decoding
arXiv:2610.10929v1 Announce Type: new Abstract: Speculative decoding is a popular technique for increasing the speed…
via arXiv cs.CROpen
SIG-1168
- AI security
The Hint Weight of ML-DSA Signatures Is Key-Dependent: An Empirical Study across the Three FIPS 204 Parameter Sets
arXiv:2610.10992v1 Announce Type: new Abstract: Every ML-DSA (FIPS 204) signature carries a public hint vector h. We…
via arXiv cs.CROpen
SIG-1169
- Agents
- Defence & detection
NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents
arXiv:2610.11030v1 Announce Type: new Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per…
via arXiv cs.CROpen
SIG-1170
- LLMs
False Claims, Credible Images: A Red-Teaming Benchmark for Commercial Image Generators
arXiv:2610.11112v1 Announce Type: new Abstract: Image-generation models can now produce text-rich, natural-looking…
via arXiv cs.CROpen
SIG-1171
- AI security
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
arXiv:2610.11163v1 Announce Type: new Abstract: Third-party challenge-response identity verification (TP-CRIV) enables…
via arXiv cs.CROpen
SIG-1172
- Privacy & data
BRACE: Differential Privacy for Dense Associative Memory with LSR Energy
arXiv:2610.11218v1 Announce Type: new Abstract: Dense associative memory (DAM) provides an energy-based framework for…
via arXiv cs.CROpen
SIG-1173
- AI security
🏴☠️ Nightspire has just published a new victim : Mäntelhaus Kaiser GmbH & Co. KG
[AI generated] N/A I don't have reliable, verifiable information about a company called "Mäntelhaus Kaiser GmbH & Co…
via ransomware.liveOpen
SIG-1174
- AI security
🏴☠️ Nightspire has just published a new victim : INAPI
[AI generated] N/A INAPI commonly refers to Chile's Instituto Nacional de Propiedad Industrial (National Institute of Industrial Property), a Chilean government agency responsible for registering…
via ransomware.liveOpen
SIG-1175
- AI security
🏴☠️ Nightspire has just published a new victim : WAGA Enterprises Architects LLC
[AI generated] N/A I don't have reliable, verifiable information about a company specifically named "WAGA Enterprises…
via ransomware.liveOpen
SIG-1176
- AI security
🏴☠️ Nightspire has just published a new victim : Sangre de Cristo Arts and Conference Center
[AI generated] Sangre de Cristo Arts and Conference Center is a nonprofit cultural organization located in Pueblo…
via ransomware.liveOpen
SIG-1177
- AI security
🏴☠️ Nightspire has just published a new victim : Vietnam SuperPort
[AI generated] N/A I don't have verified, reliable information about a specific company called "Vietnam SuperPort."…
via ransomware.liveOpen
SIG-1178
- Agents
- Defence & detection
What the 2026 Microsoft Digital Defense Report reveals about AI, identity, and the future of cybersecurity
Key Takeaways Identity is the common thread. The Microsoft Digital Defense Report 2026 shows identity sprawl, non-human…
via SpecterOpsOpen
SIG-1179
- AI security
🏴☠️ Nightspire has just published a new victim : Valvorobica Industirale S.p.A
[AI generated] N/A I don't have reliable, verifiable information about a company by this name ("Valvorobica Industriale S.p.A"). Rather than fabricate details about its operations, industry…
via ransomware.liveOpen
SIG-1180
- Policy & governance
Recorded Future Introduces AI Infrastructure Indicator Lists, Strengthening AI Governance
Today, Recorded Future is announcing AI Infrastructure Indicator Lists, curated datasets for security teams to…
via Recorded FutureOpen