Tag: ml
-
NDSS 2025 Secure Data Analytics
Session 10A: Confidential Computing 2 Authors, Creators & Presenters: Byeongwook Kim (Seoul National University), Jaewon Hur (Seoul National University), Adil Ahmad (Arizona State University), Byoungyoung Lee (Seoul National University) PAPER Secure Data Analytics in Apache Spark with Fine-grained Policy Enforcement and Isolated Execution Cloud based Spark platform is a tempting approach for sharing data, as…
-
NDSS 2025 Secure Data Analytics
Session 10A: Confidential Computing 2 Authors, Creators & Presenters: Byeongwook Kim (Seoul National University), Jaewon Hur (Seoul National University), Adil Ahmad (Arizona State University), Byoungyoung Lee (Seoul National University) PAPER Secure Data Analytics in Apache Spark with Fine-grained Policy Enforcement and Isolated Execution Cloud based Spark platform is a tempting approach for sharing data, as…
-
NDSS 2025 Secure Data Analytics
Session 10A: Confidential Computing 2 Authors, Creators & Presenters: Byeongwook Kim (Seoul National University), Jaewon Hur (Seoul National University), Adil Ahmad (Arizona State University), Byoungyoung Lee (Seoul National University) PAPER Secure Data Analytics in Apache Spark with Fine-grained Policy Enforcement and Isolated Execution Cloud based Spark platform is a tempting approach for sharing data, as…
-
Machine learningpowered Android Trojans bypass script-based Ad Click detection
A new Android click-fraud trojan family uses TensorFlow ML to visually detect and tap ads, bypassing traditional script-based click techniques. Researchers at cybersecurity firm Dr.Web discovered a new Android click-fraud trojan family that uses TensorFlow.js ML models to visually detect and tap ads, avoiding traditional script-based methods. The malware is distributed via Xiaomi’s GetApps, it…
-
New AI-Powered Android Malware Automatically Clicks Ads on Infected Devices
A sophisticated new Android malware family dubbed >>Android.Phantom<>phantom<>signaling<< controlled from the hxxps://dllpgd[.]click command server. The ML model downloads from hxxps://app-download[.]cn-wlcb[.]ufileos[.]com and analyzes screenshots of virtual screens to identify and automatically click ad […] The post New AI-Powered Android Malware Automatically Clicks Ads on Infected Devices appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform. First…
-
Python-Bibliotheken für Hugging-Face-Modelle vergiftet
Tags: ai, apple, cve, exploit, intelligence, malware, ml, network, nvidia, rce, remote-code-execution, tool, vulnerabilityPython-Libraries sind mit manipulierten Metadaten in KI-Modellen infiziert und können beim Laden Schadcode ausgeführen.NeMo, Uni2TS und FlexTok, Python-Bibliotheken für Künstliche Intelligenz (KI) und Machine Learning (ML), die in Hugging-Face-Modellen verwendet werden, haben gravierende Schwächen. Wie Forschende von Palo Alto Networks’ Unit 42 herausgefunden haben, können Kriminelle diese nutzen, um Schadcode in Metadaten zu verstecken. Einmal…
-
For application security: SCA, SAST, DAST and MAST. What next?
Tags: advisory, ai, application-security, automation, best-practice, business, cisa, cisco, cloud, compliance, container, control, cve, data, exploit, flaw, framework, gartner, government, guide, ibm, incident response, infrastructure, injection, kubernetes, least-privilege, ml, mobile, network, nist, resilience, risk, sbom, service, software, sql, supply-chain, threat, tool, training, update, vulnerability, waf<img loading="lazy" decoding="async" src="https://b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?quality=50&strip=all&w=1024" alt="Chart: Posture, provenance and proof." class="wp-image-4115680" srcset="https://b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?quality=50&strip=all 1430w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=300%2C168&quality=50&strip=all 300w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=768%2C431&quality=50&strip=all 768w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=1024%2C575&quality=50&strip=all 1024w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=1240%2C697&quality=50&strip=all 1240w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=150%2C84&quality=50&strip=all 150w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=854%2C480&quality=50&strip=all 854w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=640%2C360&quality=50&strip=all 640w, b2b-contenthub.com/wp-content/uploads/2026/01/posture-provenance-proof.jpg?resize=444%2C250&quality=50&strip=all 444w” width=”1024″ height=”575″ sizes=”auto, (max-width: 1024px) 100vw, 1024px” /> Sunil GentyalaOver the past year the community has admitted the obvious: the battleground is the software supply chain and…
-
NDSS 2025 ProbeNot: Protecting Pre-trained Encoders From Malicious Probing
Session 7D: ML Security Authors, Creators & Presenters: Ruyi Ding (Northeastern University), Tong Zhou (Northeastern University), Lili Su (Northeastern University), Aidong Adam Ding (Northeastern University), Xiaolin Xu (Northeastern University), Yunsi Fei (Northeastern University) PAPER Probe-Me-Not: Protecting Pre-Trained Encoders From Malicious Probing Adapting pre-trained deep learning models to customized tasks has become a popular choice for…
-
NDSS 2025 A New PPML Paradigm For Quantized Models
Session 7D: ML Security Authors, Creators & Presenters: Tianpei Lu (The State Key Laboratory of Blockchain and Data Security, Zhejiang University), Bingsheng Zhang (The State Key Laboratory of Blockchain and Data Security, Zhejiang University), Xiaoyuan Zhang (The State Key Laboratory of Blockchain and Data Security, Zhejiang University), Kui Ren (The State Key Laboratory of Blockchain…
-
NDSS 2025 DLBox: New Model Training Framework For Protecting Training Data
Session 7D: ML Security Authors, Creators & Presenters: Jaewon Hur (Seoul National University), Juheon Yi (Nokia Bell Labs, Cambridge, UK), Cheolwoo Myung (Seoul National University), Sangyun Kim (Seoul National University), Youngki Lee (Seoul National University), Byoungyoung Lee (Seoul National University) PAPER DLBox: New Model Training Framework For Protecting Training Data Sharing training data for deep…
-
NDSS 2025 Understanding Data Importance In Machine Learning Attacks
Session 7D: ML Security Authors, Creators & Presenters: Rui Wen (CISPA Helmholtz Center for Information Security), Michael Backes (CISPA Helmholtz Center for Information Security), Yang Zhang (CISPA Helmholtz Center for Information Security) PAPER Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm? Machine learning has revolutionized numerous domains, playing a crucial…
-
NDSS 2025 AlphaDog: No-Box Camouflage Attacks Via Alpha Channel Oversight
Session 7D: ML Security Authors, Creators & Presenters: Qi Xia (University of Texas at San Antonio), Qian Chen (University of Texas at San Antonio) PAPER AlphaDog: No-Box Camouflage Attacks via Alpha Channel Oversight Traditional black-box adversarial attacks on computer vision models face significant limitations, including intensive querying requirements, time-consuming iterative processes, a lack of universality,…
-
Demystifying risk in AI
Tags: access, ai, best-practice, bsi, business, ciso, cloud, compliance, control, corporate, csf, cyber, cybersecurity, data, framework, google, governance, group, infrastructure, intelligence, ISO-27001, LLM, mitre, ml, monitoring, nist, PCI, risk, risk-management, strategy, technology, threat, training, vulnerabilityThe data that is inserted in a request.This data is evaluated by a training model that involves an entire architecture.The result of the information that will be delivered From an information security point of view. That is the point that we, information security professionals, must judge in the scope of evaluation from the perspective of…
-
Best Enterprise Data Solutions in 2025: Real-Time Foundations for AI at Scale
Explore the best enterprise data solutions powering real-time, governed, and scalable AI platforms across analytics, ML, and operations. First seen on securityboulevard.com Jump to article: securityboulevard.com/2025/12/best-enterprise-data-solutions-in-2025-real-time-foundations-for-ai-at-scale/
-
PickleScan Uncovers 0-Day Vulnerabilities Allowing Arbitrary Code Execution via Malicious PyTorch Models
JFrog Security Research has uncovered three critical zero-day vulnerabilities in PickleScan, a widely-adopted industry-standard tool for scanning machine learning models and detecting malicious content. These vulnerabilities would enable attackers to completely bypass PickleScan’s malware detection mechanisms, potentially facilitating large-scale supply chain attacks by distributing malicious ML models containing undetectable code. The discoveries underscore a fundamental…
-
Wie Unternehmen sich gegen neue KI-Gefahren wappnen
Tags: ai, china, cyberattack, cyersecurity, hacker, hacking, injection, iran, ml, penetration-testing, phishing, risk, tool, vulnerabilityKI ist nicht nur ein Tool für Hacker, sondern kann auch selbst zur Gefahr werden.In der Welt der Cybersicherheit gibt es ein grundlegendes Prinzip, das auf den ersten Blick widersprüchlich klingen mag: ‘Wir hacken, bevor Cyberkriminelle die Gelegenheit dazu bekommen.” Um dies umzusetzen und Produktionsstraßen oder Maschinen zu schützen, setzen Unternehmen wie Siemens auf zwei…
-
Wie Unternehmen sich gegen neue KI-Gefahren wappnen
Tags: ai, china, cyberattack, cyersecurity, hacker, hacking, injection, iran, ml, penetration-testing, phishing, risk, tool, vulnerabilityKI ist nicht nur ein Tool für Hacker, sondern kann auch selbst zur Gefahr werden.In der Welt der Cybersicherheit gibt es ein grundlegendes Prinzip, das auf den ersten Blick widersprüchlich klingen mag: ‘Wir hacken, bevor Cyberkriminelle die Gelegenheit dazu bekommen.” Um dies umzusetzen und Produktionsstraßen oder Maschinen zu schützen, setzen Unternehmen wie Siemens auf zwei…
-
CYFIRMA FireTail: Working Together for Complete Visibility and Robust API Security FireTail Blog
Tags: ai, api, attack, cloud, cyber, data, detection, intelligence, leak, ml, open-source, risk, saas, threat, vulnerabilityNov 11, 2025 – Alan Fagan – CYFIRMA is an external threat landscape management platform that combines cyber intelligence with attack surface discovery and digital risk protection to deliver early warning, personalized, contextual, outside-in, and multi-layered insights. The company’s cloud-based AI and ML-powered analytics platforms provide deep insights into the external cyber landscape, helping clients…
-
CYFIRMA FireTail: Working Together for Complete Visibility and Robust API Security FireTail Blog
Tags: ai, api, attack, cloud, cyber, data, detection, intelligence, leak, ml, open-source, risk, saas, threat, vulnerabilityNov 11, 2025 – Alan Fagan – CYFIRMA is an external threat landscape management platform that combines cyber intelligence with attack surface discovery and digital risk protection to deliver early warning, personalized, contextual, outside-in, and multi-layered insights. The company’s cloud-based AI and ML-powered analytics platforms provide deep insights into the external cyber landscape, helping clients…
-
CYFIRMA FireTail: Working Together for Complete Visibility and Robust API Security FireTail Blog
Tags: ai, api, attack, cloud, cyber, data, detection, intelligence, leak, ml, open-source, risk, saas, threat, vulnerabilityNov 11, 2025 – Alan Fagan – CYFIRMA is an external threat landscape management platform that combines cyber intelligence with attack surface discovery and digital risk protection to deliver early warning, personalized, contextual, outside-in, and multi-layered insights. The company’s cloud-based AI and ML-powered analytics platforms provide deep insights into the external cyber landscape, helping clients…
-
Notable post-quantum cryptography initiatives paving the way toward Q-Day
Tags: attack, awareness, cisa, cisco, communications, computer, computing, crypto, cryptography, cyber, cybersecurity, data, encryption, finance, framework, google, government, group, guide, ibm, infrastructure, intelligence, Internet, iot, linux, microsoft, mitre, ml, nist, nvidia, open-source, service, side-channel, software, supply-chain, technology, theft, threat, tool, vulnerabilityIndustry heavyweights line up behind PQC: Google”¯Chrome became the first mainstream browser to support hybrid post”‘quantum key exchanges by default late last year.The approach combines classical elliptic-curve encryption, for backwards compatibility, with lattice-based PQC derived from ML-KEM.Other industry giants, including Amazon and IBM, have also begun laying foundations for quantum-safe cryptography. For example, IBM has…
-
Notable post-quantum cryptography initiatives paving the way toward Q-Day
Tags: attack, awareness, cisa, cisco, communications, computer, computing, crypto, cryptography, cyber, cybersecurity, data, encryption, finance, framework, google, government, group, guide, ibm, infrastructure, intelligence, Internet, iot, linux, microsoft, mitre, ml, nist, nvidia, open-source, service, side-channel, software, supply-chain, technology, theft, threat, tool, vulnerabilityIndustry heavyweights line up behind PQC: Google”¯Chrome became the first mainstream browser to support hybrid post”‘quantum key exchanges by default late last year.The approach combines classical elliptic-curve encryption, for backwards compatibility, with lattice-based PQC derived from ML-KEM.Other industry giants, including Amazon and IBM, have also begun laying foundations for quantum-safe cryptography. For example, IBM has…