Latest news
-
AI Security via arXiv cs.CR
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
arXiv:2610.30193v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage…
-
AI Security via arXiv cs.CR
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
arXiv:2610.30202v1 Announce Type: new Abstract: With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection…
-
AI Security via arXiv cs.CR
Parameters efficient language model with latent cross-attention for IoT intrusion detection
arXiv:2610.30222v1 Announce Type: new Abstract: Language models have shown strong potential for intrusion detection, but their high memory and computational demands make…
-
AI Security via arXiv cs.CR
PhishGen: Understanding LLM Capabilities in Automated Phishing Website Generation
arXiv:2610.30226v1 Announce Type: new Abstract: Phishing relies on visual deception, traditionally requiring web-development skills or pre-built kits.
-
AI Security via arXiv cs.CR
Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models
arXiv:2610.30348v1 Announce Type: new Abstract: Post-generation safety checkers are widely employed in diffusion-model pipelines to prevent unsafe generated content from…
-
Vulnerabilities via arXiv cs.CR
Who Patches the Lightning Network? Evidence from Release Lines in Gossip, 2023-2026
arXiv:2610.30350v1 Announce Type: new Abstract: Every implementation of Bitcoin's Lightning payment network disclosed security vulnerabilities in 2026, and every…
-
AI Security via arXiv cs.CR
The Psychology of an AI Hacker
arXiv:2610.30361v1 Announce Type: new Abstract: Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous…
-
AI Security via arXiv cs.CR
Data-Void Exploits in Web-Searching LLMs
arXiv:2610.30365v1 Announce Type: new Abstract: Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through…
- Advertisement
-
Breaches via arXiv cs.CR
Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT
arXiv:2610.30383v1 Announce Type: new Abstract: NIST standardised ML-KEM and ML-DSA in 2024 for post-quantum key establishment and digital signatures. Both compute…
-
Breaches via arXiv cs.CR
HAWC-Leak: Heterogeneous Architecture Workload Classification utilizing Side-Channel Leakage
arXiv:2610.30400v1 Announce Type: new Abstract: Modern heterogeneous computing platforms, which integrate general-purpose processors with specialized accelerators such…
-
AI Security via arXiv cs.CR
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
arXiv:2610.30418v1 Announce Type: new Abstract: Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled…
-
AI Security via arXiv cs.CR
Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
arXiv:2610.30439v1 Announce Type: new Abstract: Recent large reasoning models can infer where ordinary photos were taken using only visual information, creating a…
-
AI Security via arXiv cs.CR
Membership Inference Attack on Private Evolution
arXiv:2610.30514v1 Announce Type: new Abstract: Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly…
-
AI Security via arXiv cs.CR
Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
arXiv:2610.30516v1 Announce Type: new Abstract: In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as…
-
AI Security via arXiv cs.CR
Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset
arXiv:2610.30576v1 Announce Type: new Abstract: A fundamental paradox plagues the deployment of Machine Learning in cybersecurity: supervised models generalize poorly to…
-
AI Security via arXiv cs.CR
HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models
arXiv:2610.30601v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly…
-
AI Security via arXiv cs.CR
Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models
arXiv:2610.30626v1 Announce Type: new Abstract: The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting…
-
AI Security via arXiv cs.CR
Your Token Is Gone: A Token-Consumption Countermeasure for Disrupting LLM-Based Scam Systems
arXiv:2610.30666v1 Announce Type: new Abstract: LLM-based scam systems increasingly combine adaptive dialogue, persistent context, external tools, and multi-agent…
-
AI Security via arXiv cs.CR
AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things
arXiv:2610.30713v1 Announce Type: new Abstract: Modern Industrial Internet of Things (IIoT) im- plementations now connect edge gateways, cloud dashboards and business…
-
AI Security via arXiv cs.CR
Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
arXiv:2610.30798v1 Announce Type: new Abstract: Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time…