ChatGPT Tricked Into Solving CAPTCHAs 2025-09-19 at 14:30 By Ionut Arghire The AI agent was able to solve different types of CAPTCHAs and adjusted its cursor movements to better mimic human behavior. The post ChatGPT Tricked Into Solving CAPTCHAs appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to […]
React to this headline:
ChatGPT Tricked Into Solving CAPTCHAs Read More »
ChatGPT Targeted in Server-Side Data Theft Attack 2025-09-18 at 18:49 By Eduard Kovacs OpenAI has fixed this zero-click attack method called by researchers ShadowLeak. The post ChatGPT Targeted in Server-Side Data Theft Attack appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to this headline:
React to this headline:
ChatGPT Targeted in Server-Side Data Theft Attack Read More »
Irregular Raises $80 Million for AI Security Testing Lab 2025-09-17 at 17:34 By Eduard Kovacs Irregular is testing the cybersecurity capabilities of AI models, including Anthropic’s Claude and OpenAI’s ChatGPT. The post Irregular Raises $80 Million for AI Security Testing Lab appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
React to this headline:
Irregular Raises $80 Million for AI Security Testing Lab Read More »
Scalekit Raises $5.5 Million to Secure AI Agent Authentication 2025-09-17 at 15:03 By Ionut Arghire The startup provides an authentication stack that secures both incoming authentication and outgoing agent actions. The post Scalekit Raises $5.5 Million to Secure AI Agent Authentication appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source
React to this headline:
Scalekit Raises $5.5 Million to Secure AI Agent Authentication Read More »
CrowdStrike to Acquire Pangea to Launch AI Detection and Response (AIDR) 2025-09-17 at 01:45 By SecurityWeek News Acquisition extends CrowdStrike’s Falcon platform into AI security, introducing AI Detection and Response (AIDR) to protect enterprise models, agents, and applications across the full AI lifecycle. The post CrowdStrike to Acquire Pangea to Launch AI Detection and Response
React to this headline:
CrowdStrike to Acquire Pangea to Launch AI Detection and Response (AIDR) Read More »
Check Point to Acquire AI Security Firm Lakera 2025-09-16 at 22:04 By SecurityWeek News Move highlights rising demand for AI-native security as enterprises face new risks from generative models and autonomous agents The post Check Point to Acquire AI Security Firm Lakera appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original
React to this headline:
Check Point to Acquire AI Security Firm Lakera Read More »
ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails 2025-09-16 at 14:05 By Eduard Kovacs EdisonWatch researchers demonstrated the new hack after OpenAI added support for MCP tools in ChatGPT. The post ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
React to this headline:
ChatGPT’s New Calendar Integration Can Be Abused to Steal Emails Read More »
F5 to Acquire CalypsoAI for $180 Million 2025-09-12 at 14:35 By Eduard Kovacs F5 is buying CalypsoAI for its adaptive AI inference security solutions, which will be integrated into its Application Delivery and Security Platform. The post F5 to Acquire CalypsoAI for $180 Million appeared first on SecurityWeek. This article is an excerpt from SecurityWeek
React to this headline:
F5 to Acquire CalypsoAI for $180 Million Read More »
AI Emerges as the Hope—and Risk—for Overloaded SOCs 2025-09-11 at 14:30 By Kevin Townsend With security teams drowning in alerts, many suppress detection rules and accept hidden risks. AI promises relief through automation and triage—but without human oversight, it risks becoming part of the problem. The post AI Emerges as the Hope—and Risk—for Overloaded SOCs
React to this headline:
AI Emerges as the Hope—and Risk—for Overloaded SOCs Read More »
PromptLock Only PoC, but AI-Powered Ransomware Is Real 2025-09-08 at 17:37 By Ionut Arghire PromptLock is only a prototype of LLM-orchestrated ransomware, but hackers already use AI in file encryption and extortion attacks. The post PromptLock Only PoC, but AI-Powered Ransomware Is Real appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
React to this headline:
PromptLock Only PoC, but AI-Powered Ransomware Is Real Read More »
How to Close the AI Governance Gap in Software Development 2025-09-05 at 18:14 By Matias Madou Widespread adoption of AI coding tools accelerates development—but also introduces critical vulnerabilities that demand stronger governance and oversight. The post How to Close the AI Governance Gap in Software Development appeared first on SecurityWeek. This article is an excerpt
React to this headline:
How to Close the AI Governance Gap in Software Development Read More »
Academics Build AI-Powered Android Vulnerability Discovery and Validation Tool 2025-09-05 at 16:44 By Ionut Arghire Called A2, the framework mimics human analysis to identify vulnerabilities in Android applications and then validates them. The post Academics Build AI-Powered Android Vulnerability Discovery and Validation Tool appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View
React to this headline:
Academics Build AI-Powered Android Vulnerability Discovery and Validation Tool Read More »
Stealthy attack serves poisoned web pages only to AI agents 2025-09-05 at 14:30 By Zeljka Zorz AI agents can be tricked into covertly performing malicious actions by websites that are hidden from regular users’ view, JFrog AI architect Shaked Zychlinski has found. This novel approach allows attackers to inject prompts / instructions into these autonomous
React to this headline:
Stealthy attack serves poisoned web pages only to AI agents Read More »
AI Supply Chain Attack Method Demonstrated Against Google, Microsoft Products 2025-09-04 at 16:00 By Eduard Kovacs An AI supply chain issue named Model Namespace Reuse can allow attackers to deploy malicious models and achieve code execution. The post AI Supply Chain Attack Method Demonstrated Against Google, Microsoft Products appeared first on SecurityWeek. This article is
React to this headline:
AI Supply Chain Attack Method Demonstrated Against Google, Microsoft Products Read More »
Hackers Weaponize Trust with AI-Crafted Emails to Deploy ScreenConnect 2025-08-27 at 20:01 By Kevin Townsend AI-powered phishing attacks leverage ConnectWise ScreenConnect for remote access, underscoring their sophistication. The post Hackers Weaponize Trust with AI-Crafted Emails to Deploy ScreenConnect appeared first on SecurityWeek. This article is an excerpt from SecurityWeek View Original Source React to this
React to this headline:
Hackers Weaponize Trust with AI-Crafted Emails to Deploy ScreenConnect Read More »
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 React to this headline:
React to this headline:
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 React to
React to this headline:
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
React to this headline:
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
React to this headline:
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
React to this headline:
Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise Read More »