AI spam filters are getting suckered by old-school text salting
Turns out decades-old email tricks still work against some LLM-powered email filters
Explore the intersection of AI and cybersecurity. Stay informed on AI-driven security trends, tools, and threats in the ever-evolving digital landscape.
Search across headline titles and summaries.
Background for this topic.
Artificial intelligence (AI) describes computer systems that perform tasks such as recognizing patterns, making predictions, understanding language, or generating content. In security reporting, the term commonly includes machine-learning models used for detection and analysis, as well as generative AI applications that produce text, code, images, or other outputs.
AI can help analyze security telemetry, prioritize vulnerabilities, and support investigations, but its outputs can be wrong or manipulated. Important attack surfaces include prompt injection that steers an application into unintended actions, sensitive data being exposed through prompts or model outputs, and excessive permissions granted to AI systems that use external tools. Models can also be degraded by poisoned training data or evaded with carefully crafted inputs. Practitioners should protect training and operational data, limit model access and tool permissions, test for adversarial behavior, and require appropriate human validation before high-impact decisions.
Weekly headline count for the current query.
Turns out decades-old email tricks still work against some LLM-powered email filters
Adapting existing local LLM project for security and sovereignty purposes and hopes to one day match Mythos
Data purges deemed an example of 'misaligned behavior' that upstart is working to avoid
Models demand trust without offering verification
Researcher confirms the uploads have stopped, but says xAI's privacy command was not what fixed them
Human did 10% of the job, AI did 90%
More patches mean more reasons to buy Redmond’s auto-patching tools
More fun with AI jailbreaks, this time at the workflow level
'GhostApproval' problem highlights human-in-the-loop fails
Per usual, there's no fix – or even any documentation – for GitLost
Majority report AI-related security incidents or vulnerabilities
MeetingTV wants to see the evidence
Don't count on the LLM to return your data - even if you pay up
People trust their AI assistants and it's easy to abuse this trust
You don't need Mythos or GPT-5.5-Cyber to find a vuln to exploit when the world's password habits are so sloppy
Time to start praying to the goddess of wisdom and war
Researchers warn many AI coding assistants now execute commands from project configurations
Qihoo 360, which the US has banned, says it’s needed as a deterrent to weaponized Anthropic models
200+ C2 servers linked to StealC and Amadey shut down
Bosses told to step up and get cybersecurity right