PromptLock: First AI-Powered Ransomware Emerges 2025-08-27 at 14:51 By Ionut Arghire Proof-of-concept ransomware uses AI models to generate attack scripts in real time. The post PromptLock: First AI-Powered Ransomware Emerges appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
PromptLock: First AI-Powered Ransomware Emerges Read More »
Beyond the Prompt: Building Trustworthy Agent Systems 2025-08-26 at 18:03 By Stu Sjouwerman Building secure AI agent systems requires a disciplined engineering approach focused on deliberate architecture and human oversight. The post Beyond the Prompt: Building Trustworthy Agent Systems appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Beyond the Prompt: Building Trustworthy Agent Systems Read More »
AI Systems Vulnerable to Prompt Injection via Image Scaling Attack 2025-08-26 at 13:47 By Eduard Kovacs Researchers show how popular AI systems can be tricked into processing malicious instructions by hiding them in images. The post AI Systems Vulnerable to Prompt Injection via Image Scaling Attack appeared first on SecurityWeek. This article is an excerpt
AI Systems Vulnerable to Prompt Injection via Image Scaling Attack Read More »
Managing the Trust-Risk Equation in AI: Predicting Hallucinations Before They Strike 2025-08-11 at 17:17 By Kevin Townsend New physics-based research suggests large language models could predict when their own answers are about to go wrong — a potential game changer for trust, risk, and security in AI-driven systems. The post Managing the Trust-Risk Equation in
Managing the Trust-Risk Equation in AI: Predicting Hallucinations Before They Strike Read More »
Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise 2025-08-08 at 21:34 By Kevin Townsend Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses. The post Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise appeared first on SecurityWeek. This article is an
Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise Read More »
Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation 2025-08-07 at 02:36 By Eduard Kovacs Zenity has shown how AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially crafted prompts. The post Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation appeared first on
Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation Read More »
Project Ire: Microsoft’s autonomous malware detection AI agent 2025-08-05 at 19:45 By Zeljka Zorz Microsoft is working on a AI agent whose main goal is autonomous malware detection and the prototype – dubbed Project Ire – is showing great potential, the company has announced on Tuesday. Tested on a dataset of known malicious and benign
Project Ire: Microsoft’s autonomous malware detection AI agent Read More »
Vibe Coding: When Everyone’s a Developer, Who Secures the Code? 2025-08-05 at 16:42 By Kevin Townsend As AI makes software development accessible to all, security teams face a new challenge: protecting applications built by non-developers at unprecedented speed and scale. The post Vibe Coding: When Everyone’s a Developer, Who Secures the Code? appeared first on
Vibe Coding: When Everyone’s a Developer, Who Secures the Code? Read More »
Microsoft Offers $5 Million at Zero Day Quest Hacking Contest 2025-08-05 at 11:38 By Ionut Arghire Research demonstrating high-impact cloud and AI security flaws will be rewarded at Microsoft’s Zero Day Quest competition in spring 2026. The post Microsoft Offers $5 Million at Zero Day Quest Hacking Contest appeared first on SecurityWeek. This article is
Microsoft Offers $5 Million at Zero Day Quest Hacking Contest Read More »
Nvidia Triton Vulnerabilities Pose Big Risk to AI Models 2025-08-04 at 21:22 By Eduard Kovacs Nvidia has patched over a dozen vulnerabilities in Triton Inference Server, including another set of vulnerabilities that threaten AI systems. The post Nvidia Triton Vulnerabilities Pose Big Risk to AI Models appeared first on SecurityWeek. This article is an excerpt
Nvidia Triton Vulnerabilities Pose Big Risk to AI Models Read More »
AI Guardrails Under Fire: Cisco’s Jailbreak Demo Exposes AI Weak Points 2025-08-04 at 16:04 By Kevin Townsend Cisco’s latest jailbreak method reveals just how easily sensitive data can be extracted from chatbots trained on proprietary or copyrighted content. The post AI Guardrails Under Fire: Cisco’s Jailbreak Demo Exposes AI Weak Points appeared first on SecurityWeek.
AI Guardrails Under Fire: Cisco’s Jailbreak Demo Exposes AI Weak Points Read More »
Noma Security Raises $100 Million for AI Security Platform 2025-07-31 at 18:34 By Eduard Kovacs Noma Security has announced a Series B funding round that will enable the company’s growth and expansion of its AI agent security solutions. The post Noma Security Raises $100 Million for AI Security Platform appeared first on SecurityWeek. This article
Noma Security Raises $100 Million for AI Security Platform Read More »
Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data 2025-07-31 at 15:07 By Eduard Kovacs LayerX has disclosed an AI chatbot hacking method via web browser extensions it has named ‘man-in-the-prompt’. The post Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data appeared first on SecurityWeek. This article is an excerpt
Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data Read More »
Cyata Emerges From Stealth With $8.5 Million in Funding 2025-07-30 at 15:16 By Ionut Arghire The Israeli startup helps organizations identify, monitor, and control AI agents across their environments. The post Cyata Emerges From Stealth With $8.5 Million in Funding appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Cyata Emerges From Stealth With $8.5 Million in Funding Read More »
Flaw in Vibe Coding Platform Base44 Exposed Private Enterprise Applications 2025-07-30 at 14:18 By Eduard Kovacs Base44 owner Wix quickly patched a critical authentication bypass vulnerability discovered by researchers at Wiz. The post Flaw in Vibe Coding Platform Base44 Exposed Private Enterprise Applications appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
Flaw in Vibe Coding Platform Base44 Exposed Private Enterprise Applications Read More »
Promptfoo Raises $18.4 Million for AI Security Platform 2025-07-29 at 16:03 By Ionut Arghire Promptfoo has raised $18.4 million in Series A funding to help organizations secure LLMs and generative AI applications. The post Promptfoo Raises $18.4 Million for AI Security Platform appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Promptfoo Raises $18.4 Million for AI Security Platform Read More »
Dropzone AI Raises $37 Million for Autonomous SOC Analyst 2025-07-29 at 14:11 By Eduard Kovacs Dropzone AI has announced a Series B funding round led by Theory Ventures to boost its AI SOC solution. The post Dropzone AI Raises $37 Million for Autonomous SOC Analyst appeared first on SecurityWeek. This article is an excerpt from
Dropzone AI Raises $37 Million for Autonomous SOC Analyst Read More »
Creating Realistic Deepfakes Is Getting Easier Than Ever. Fighting Back May Take Even More AI 2025-07-29 at 05:01 By Associated Press Deepfakes are causing security problems for governments, businesses and individuals and making trust the most valuable currency of the digital age. The post Creating Realistic Deepfakes Is Getting Easier Than Ever. Fighting Back May
Sophisticated Koske Linux Malware Developed With AI Aid 2025-07-25 at 14:43 By Eduard Kovacs The Koske Linux malware shows how cybercriminals can use AI for payload development, persistence, and adaptivity. The post Sophisticated Koske Linux Malware Developed With AI Aid appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
Sophisticated Koske Linux Malware Developed With AI Aid Read More »
From Tech Podcasts to Policy: Trump’s New AI Plan Leans Heavily on Silicon Valley Industry Ideas 2025-07-24 at 13:18 By Associated Press President Donald Trump has unveiled a sweeping new plan for America’s “global dominance” in artificial intelligence. The post From Tech Podcasts to Policy: Trump’s New AI Plan Leans Heavily on Silicon Valley Industry