Advertisement
ChatGPT Secure Sandbox PoC Enables C2-Style Influence
A researcher demonstrated a proof-of-concept attack chain enabling C2-style influence over ChatGPT's secure sandbox environment.
Phishing Targets AI Service Users: Guard Your ChatGPT Accounts
Recent phishing campaigns impersonate popular AI services like ChatGPT to trick users into divulging credentials. Learn how to protect your accounts and data.
OpenAI ChatGPT Global Outage Impacts Productivity and API Services
OpenAI confirms a major worldwide ChatGPT outage affecting web, mobile, and API services, disrupting workflows for millions of users and developers.
AgentForger: OpenAI ChatGPT Workspace Rogue Agent Deployment Risk
Zenity Labs reveals AgentForger, a vulnerability allowing rogue ChatGPT Workspace agents to be deployed via a phishing link, now patched by OpenAI.
ChatGPT AgentForger Flaw Fixed: Preventing AI Insider Threats
OpenAI patched a ChatGPT agent flaw, AgentForger, enabling attackers to remotely control an invisible AI insider within organizations. Learn mitigation strategies.
OpenAI Tests ChatGPT for Science: Security and Safety Analysis
Leaked details confirm OpenAI is testing a specialized ChatGPT for Science subscription. Analyze the features, dual-use risks, and AI safety implications.
Advertisement
OpenAI Expands ChatGPT Account Security with New Session Controls
OpenAI rolls out Active Sessions and Lockdown Mode for ChatGPT, providing users and administrators with granular visibility into unauthorized account access.
OpenAI ChatGPT Lockdown Mode: Mitigating Prompt Injection Exfiltration
OpenAI introduces ChatGPT Lockdown Mode for personal accounts to prevent prompt injection attacks from exfiltrating sensitive data via external tools.
ChatGPT Share Link Abuse: Fake Outages Deliver Malware
Threat actors leverage ChatGPT share links to host deceptive outage pages, prompting users to download malware disguised as an official desktop app.
ChatGPT ChatGPhish Vulnerability: Web Summaries Lead to Phishing
A newly disclosed ChatGPhish vulnerability allows attackers to leverage ChatGPT's Markdown trust for prompt injections and sophisticated phishing campaigns.
GreyVibe Threat Actor Leverages AI for Cyberattack Operations
Russia-linked GreyVibe threat actors are using AI tools like ChatGPT and Gemini to enhance cyberattacks, signaling a critical evolution in TTPs.
Evolution of Modern Threats: From Stuxnet to AI-Driven Vulnerabilities
An analysis of the 20-year evolution of the cybersecurity landscape, detailing the shift from industrial sabotage to automated, AI-driven exploitation.
OpenAI Advanced Account Security: Mitigating AI Identity Risks
OpenAI releases Advanced Account Security features for ChatGPT, including FIDO2 support and session management to prevent unauthorized account access.
OpenAI Patches ChatGPT Data Exfiltration and Codex Token Flaws
OpenAI addresses high-impact vulnerabilities in ChatGPT and Codex that enabled unauthorized data exfiltration and exposure of sensitive GitHub tokens.
OpenAI ChatGPT Library: Data Privacy and Cloud Security Analysis
OpenAI launches ChatGPT Library for persistent file storage. Explore technical risks, enterprise privacy controls, and data exfiltration mitigations.
OpenAI ChatGPT Privacy Policy Update: Implications of Ad Rollout
OpenAI clarifies its stance on ChatGPT advertisements following privacy policy updates. Learn how OpenAI data collection for advertising impacts users.
Chinese Police Use ChatGPT in Influence Operations Against Japan
Chinese police reportedly used ChatGPT for politically motivated influence operations to smear Japan's PM Takaichi, highlighting AI's role in disinformation campaigns.
Data Poisoning Risks in Real-Time AI Search and Ingestion
A recent experiment highlights how rapid web scraping for AI models like Gemini and ChatGPT enables data poisoning attacks through unverified web content.