최신정보
- CVEKISA 보안공지2026-10-24PHP 신규 취약점(CVE-2026-115560) 임시 조치 권고
- CVECISA 보안권고2026-10-23CISA Adds One Known Exploited Vulnerability to Catalog
CISA has added one new vulnerability to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-110447 Collabora Online – Built-in CODE Server OS Command
- CVECISA 보안권고2026-10-23CISA Adds One Known Exploited Vulnerability to Catalog
CISA has added one new vulnerability to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-114625 Arista VeloCloud Orchestrator SQL Injection Vulnera
- arXiv cs.CR2026-10-23Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models
The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting important for ownership protection and offline auditing. Existing fingerprinting m
- arXiv cs.CR2026-10-23HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models
With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated content and assign responsibility for its use, raising
- arXiv cs.CR2026-10-23Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset
A fundamental paradox plagues the deployment of Machine Learning in cybersecurity: supervised models generalize poorly to novel, Out-of-Distribution (OoD) attacks, whereas unsupervised models often su
- arXiv cs.CR2026-10-23Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as text transmitted to a decoder, who attempts to recover it. The success of this pri
- arXiv cs.CR2026-10-23Membership Inference Attack on Private Evolution
Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly. Inference-only SDG methods, such as Private Evolution (PE), are particularly appealing,
- arXiv cs.CR2026-10-23Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
Recent large reasoning models can infer where ordinary photos were taken using only visual information, creating a serious location privacy risk even when metadata and obvious geographic identifiers a
- arXiv cs.CR2026-10-23Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical risk for agents operating over
- arXiv cs.CR2026-10-23HAWC-Leak: Heterogeneous Architecture Workload Classification utilizing Side-Channel Leakage
Modern heterogeneous computing platforms, which integrate general-purpose processors with specialized accelerators such as FPGAs, have become the standard for high-performance and embedded application
- arXiv cs.CR2026-10-23Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT
NIST standardised ML-KEM and ML-DSA in 2024 for post-quantum key establishment and digital signatures. Both compute forward number-theoretic transforms (NTTs) on secret polynomials. Published attacks
- arXiv cs.CR2026-10-23Data-Void Exploits in Web-Searching LLMs
Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized answers. This shift creates a new LL
- arXiv cs.CR2026-10-23The Psychology of an AI Hacker
Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous emotion representations in AI models can improve cybersecurity AI performance.
- arXiv cs.CR2026-10-23Who Patches the Lightning Network? Evidence from Release Lines in Gossip, 2023-2026
Every implementation of Bitcoin's Lightning payment network disclosed security vulnerabilities in 2026, and every advisory told operators to upgrade. Whether they do has never been measured, because L
- arXiv cs.CR2026-10-23Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models
Post-generation safety checkers are widely employed in diffusion-model pipelines to prevent unsafe generated content from reaching users. In this paper, we show that these safety checkers can still be
- arXiv cs.CR2026-10-23PhishGen: Understanding LLM Capabilities in Automated Phishing Website Generation
Phishing relies on visual deception, traditionally requiring web-development skills or pre-built kits. LLMs erode this barrier by generating functional websites from natural-language prompts, yet prio
- arXiv cs.CR2026-10-23Parameters efficient language model with latent cross-attention for IoT intrusion detection
Language models have shown strong potential for intrusion detection, but their high memory and computational demands make them difficult to deploy in resource-constrained IoT environments. In this wor
- arXiv cs.CR2026-10-23MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal malicious i
- arXiv cs.CR2026-10-23Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection. Ye
- arXiv cs.CR2026-10-23Self-Evolving Static Analysis via LLM Pseudo-Labeling
Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us. New frameworks, APIs, and co
- arXiv cs.CR2026-10-23When EVM Defaults Break: Three SDK Patterns for UTXO-Family Wallets
Mainstream Web3 SDKs (e.g., ethers.js, viem) bundle three coupled assumptions: an account-based ledger, a single secp256k1 signer, and input-selection-free transaction construction. These assumptions
- arXiv cs.CR2026-10-23Detecting AI Training in Datacentre Power
AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model training i
- KISA 보안공지2026-10-23Node.js 제품 보안 업데이트 권고
- KISA 보안공지2026-10-23Oracle 제품 보안 업데이트 권고
- KISA 보안공지2026-10-23Laravel 제품 보안 업데이트 권고
- CVECISA 보안권고2026-10-22Kiloview E3 NDI Encoder
View CSAF Summary Successful exploitation of this these vulnerabilities could allow an attacker to fully compromise the device. The following versions of Kiloview E3 NDI Encoder are affected: E3 Firmw
- CVECISA 보안권고2026-10-22Siemens SIMATIC S7-1500 TM MFP
View CSAF Summary Multiple vulnerabilities have been identified in the additional GNU/Linux subsystem of the SIMATIC S7-1500 TM MFP V1.1.1. Siemens is preparing fixes and recommends specific mitigatio
- CVECISA 보안권고2026-10-22Siemens SENTRON 3NA COM Fuse
View CSAF Summary SENTRON 3NA COM Fuse contains a Denial-of-Service vulnerability. Improper handling of a network management message could allow an attacker to trigger a denial-of-service (DoS) condit
- CVECISA 보안권고2026-10-22Siemens SIMATIC S7 PLCs Web Server
View CSAF Summary SIMATIC S7-1500 devices contain multiple vulnerabilities in the web server that could allow an attacker to execute malicious code in an authorized user’s browser session and perform
* RSS 피드가 제공하는 제목·링크·요약만 수집하며, 원문은 출처 링크에서 확인하세요. 한국어 AI 요약은 3차 개발 범위입니다.