// llm security

All signals tagged with this topic

Oct 31

Chinese hackers weaponized DeepSeek AI to target 200+ organizations in 11 days

CrowdStrike disclosed that China-linked actors deployed DeepSeek's open-source LLM within the ARTEX tool to conduct reconnaissance and craft phishing attacks at scale. This is the first documented case of frontier AI models being operationalized in active intrusion campaigns—not as research or proof-of-concept, but with measurable tactical advantage against 200+ targets across 11 days. The speed and breadth suggest that open LLMs have crossed a threshold: they're no longer barriers to entry for sophisticated operators but force multipliers that compress reconnaissance-to-exploitation timelines. When the same models available to Fortune 500 security teams are equally available to state-sponsored actors, advantage shifts to whoever integrates fastest into existing attack infrastructure.

theme-ai prompt injection llm security agent systems

Oct 11

AWS Agent Flaw Exposes Credential Theft Through Simple Prompts

Source: Theregister

Amazon's AgentCore system was vulnerable to a basic social engineering attack—a malicious prompt could convince the AI agent to hand over AWS credentials stored in its memory, turning a foundation model into an unwitting credential harvester. AWS shipped agentic tools without basic guardrails against prompt injection. As enterprises deploy autonomous agents with real infrastructure access, the gap between stated security postures and actual threat modeling will widen.

theme-ai model capability data privacy llm security

Sep 2

Which AI Models Actually Keep Your Secrets Private

Source: Ownersnotrenters

Claude, ChatGPT, and other consumer AI tools have radically different data retention and training practices depending on which version you pay for—a distinction most users don't understand when they paste sensitive information into the free tier. Your choice of model and subscription plan directly determines whether your inputs become training data, stay on servers indefinitely, or get deleted. This creates a hidden stratification in AI privacy that mirrors social media's free-vs-paid tiers, but with less transparency.

theme-ai llm security prompt injection ai safety

Jun 16

LLMs Are Becoming a New Vector for API Attacks

Source: The Register: Biting the hand that feeds

As applications pile permissions and rely on chain-of-command API calls, large language models have reduced the technical barrier for crafting sophisticated exploits—attackers no longer need deep API knowledge to discover and chain together vulnerabilities. Prompt engineering is now a viable hacking methodology. Defenders face attackers who can operate at human-like speed across distributed systems without traditional coding skills. Organizations betting on "secure by default" architectures will outpace those still managing sprawling permission models designed for monolithic applications.

theme-ai ai safety llm security ai-enabled attacks

Jun 3

Toronto researchers build AI-powered worm that customizes attacks per system

Source: The New York Times

A team at the University of Toronto has demonstrated that open-source language models can autonomously discover and exploit known vulnerabilities, then adapt their approach to individual targets. What was previously labor-intensive manual work is now scalable and self-directed. Researchers built a working prototype using publicly available tools, meaning defenders now face an adversary that doesn't tire and can iterate faster than human operators. The security industry will need to move beyond patching individual holes toward systemic resilience. The constraint preventing widespread AI-driven attacks has shifted from capability to incentive.