Attackers intercepting network traffic can determine the conversation topic with a chatbot despite end-to-end encrypted communication.
The post ‘Whisper Leak’ LLM Side-Channel Attack Infers User Prompt Topics appeared first on SecurityWeek.
Many Forbes AI 50 Companies Leak Secrets on GitHub
Wiz found the secrets and warned that they can expose training data, organizational structures, and private models.
The post Many Forbes AI 50 Companies Leak Secrets on GitHub appeared first on SecurityWeek.
Data Exposure Vulnerability Found in Deep Learning Tool Keras
The vulnerability is tracked as CVE-2025-12058 and it can be exploited for arbitrary file loading and conducting SSRF attacks.
The post Data Exposure Vulnerability Found in Deep Learning Tool Keras appeared first on SecurityWeek.
Researchers Hack ChatGPT Memories and Web Search Features
Tenable researchers discovered seven vulnerabilities, including ones affecting the latest GPT model.
The post Researchers Hack ChatGPT Memories and Web Search Features appeared first on SecurityWeek.
Follow Pragmatic Interventions to Keep Agentic AI in Check
Agentic AI speeds operations, but requires clear goals, least privilege, auditability, red‑teaming, and human oversight to manage opacity, misalignment, and misuse.
The post Follow Pragmatic Interventions to Keep Agentic AI in Check appeared first on SecurityWeek.
Malware Now Uses AI During Execution to Mutate and Collect Data, Google Warns
Google has released a report describing the novel ways in which malware has been using AI to adapt and evade detection.
The post Malware Now Uses AI During Execution to Mutate and Collect Data, Google Warns appeared first on SecurityWeek.
Portal26 Raises $9 Million for Gen-AI Adoption Platform
The gen-AI adoption management platform will invest the funds in accelerating growth and product innovations.
The post Portal26 Raises $9 Million for Gen-AI Adoption Platform appeared first on SecurityWeek.
How Software Development Teams Can Securely and Ethically Deploy AI Tools
To deploy AI tools securely and ethically, teams must balance innovation with accountability—establishing strong governance, upskilling developers, and enforcing rigorous code reviews.
The post How Software Development Teams Can Securely and Ethically Deploy AI Tools appeared first on SecurityWeek.
Claude AI APIs Can Be Abused for Data Exfiltration
An attacker can inject indirect prompts to trick the model into harvesting user data and sending it to the attacker’s account.
The post Claude AI APIs Can Be Abused for Data Exfiltration appeared first on SecurityWeek.
AI Security Firm Polygraf Raises $9.5 Million in Seed Funding
Polygraf AI has developed proprietary small language model (SLM) technology designed to help organizations mitigate AI risks.
The post AI Security Firm Polygraf Raises $9.5 Million in Seed Funding appeared first on SecurityWeek.
