research
286 articles with this tag
MEDIUM
INFO
INFO
INFO
INFO
INFO
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
INFO
MEDIUM
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
INFO
CRITICAL
INFO
HIGH
MEDIUM
MEDIUM
INFO
INFO
HIGH
MEDIUM
INFO
MEDIUM
INFO
HIGH
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
CRITICAL
INFO
INFO
HIGH
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
HIGH
HIGH
HIGH
INFO
INFO
INFO
INFO
INFO
INFO
INFO
MEDIUM
INFO
INFO
MEDIUM
INFO
INFO
INFO
INFO
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
LOW
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
Getting a stranger’s phone kicked off the cellular network costs a few dollars
I Turned the Open Internet Into a Minecraft World
Milljarðaverðmæti undir í nýtingu á rauðátu
Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety
Researching Employment Scams
10 most critical LLM vulnerabilities
Apple mach_o Archive Parser Integer Underflow Vulnerability
Anthropic reveals fourth likely crime committed by its AI
Botnveiðarfæri skila um 24 milljóna tonna afla á ári
OpenAI just hit a milestone on the road to self-improving AI
OpenAI's rebel agent swarm died young, but its chilling logs live on
Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel
OpenAI agents discussed ways to escape their sandbox on public wiki
Abliteration.ai launches service for uncensored AI models
39 New Methods That Compromise Passkey Authentication
AI Coding Agents Are Installing Unknown/Untrusted Code on Corporate Networks
GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests
The story behind the intelligence
An AI CAPTCHA solver talked itself out of the right answer
Breaking the Seal: Static Deobfuscation of JSCeal’s Compiled V8 Bytecode
Áhrif Íslands í rannsókninni einstök
Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety
1,200 OpenAI agents colluded to cheat evaluations in lead-up to Hugging Face attack
OpenAI Says Reward Hacking Drove AI Agents to Exploit Zero-Days and Breach Hugging Face
The AI ‘Ghosts’ Contaminating Academic Publishing
OpenAI explains how its AI agents did crime and attacked Hugging Face
Why human-speed defense has failed
New attack lets hackers plant hidden instructions in AI memory with a single prompt
How to break secure boot without touching any cryptography
More Incidents of AIs Going Rogue in Cybersecurity Challenges
BTR Reforged: Weaponizing Defender’s Remediation Driver as a Kernel Operation Primitive
Researchers find a loophole that lets expired credit cards make unauthorized payments
OpenAI puts major frontier AI training run on hold over cyber risks
Expired credit cards revived by researchers to make unauthorized payments
AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files
OpenAI tightens defenses after AI agents breach research environment
Chinese AI model GLM-5.3 shows advanced bug-finding capabilities
Anthropic details new AI model, raises risk assessment for internal system tampering
When companies get specific about AI, revenue growth looks different
Amid AI-Driven Bug Tsunami, NIST Looks to…AI
The Model Is the Malware | What Four Agentic Intrusions Tell Defenders
Can AI do novel security research? Meet the HTTP Terminator
Microsoft wants you to rethink your approach to cyber defense
OpenAI Pauses Some Development of Astra Model on Security Concerns
GPT-5.6-Cyber refuses security researchers’ requests far less often
OpenAI's new Astra model may pose critical cybersecurity risks
Polish researchers find thousands of public websites vulnerable to cyberattacks
Outdated Cybercrime Laws Put Security Researchers at Risk
OpenAI locks down Astra over potential critical cyber capabilities
Beyond Prompt Injection: Hacking Apple's Private Cloud Compute
Þrjú byggkorn staðfesta aldur landnámsbyggðar
Devs to Anthropic, OpenAI, Cursor, and friends: Make security and privacy the default
Sensitive Info Goes Into ‘No Reply’ Emails Constantly. This Guy Sees It All
OpenAI pledges to add Astra security as Anthropic loosens Fable's leash
More than half of AI-generated patches are broken
Déjà Vu? Meta's AI Escapes Testing Lab in Hacking Joyride
Áslaug Arna ráðin til Fenris Creations í London
How the famed USENIX Security conf is managing a flood of papers in the AI era
Expanding AI Benchmarks in Cybersecurity Beyond Vulnerability Discovery
Adversarial Clothing Designed to Fool Facial Recognition Systems
Black Hat 2026: OpenAI reveals agents planned ‘collective attacks’ via secret ‘message board’
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
Prompt injection isn't the bug, AI agent frameworks are
Code review used to be the only way to catch these bugs
Prompt Injection Remains Biggest LLM Risk, Despite Limited Incidents
Most small businesses survive data breaches. Here's how to make sure yours does too
Your enterprise AI footprint is about three times bigger than your model list
AI researchers let models off the leash – then watched as they tried to add malware to a FOSS project
AISI, OpenAI report more ‘unsanctioned’ model hacks
Bugtraq is back 🥹
The Frontier AI Vulnerability Burst: Industrializing Autonomous Zero-Day Discovery in Open-Source Software
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
When AI doesn’t know the target is real
frontier class vulnerabilities: it gets worse before it (maybe) gets better
Enhancing AI security through global AI red teaming
The State of Network Infrastructure Security 2026
TrendAI™ Joins Nvidia’s Open Secure AI Alliance: Closing the Gap Between AI Builders and AI Defenders
Black Hat special: Rewind and revisit
AI Scammers Are Better at Building Trust Than Humans
Mythos uncovers crypto weaknesses that went unknown for years
Closed models refuse to help researcher swat Linux bug
New AI security approach analyzes model internals
Mythos takes its first shot at post-quantum cryptography
Just 1% of AI-Discovered Vulnerabilities Exploited in the Wild, Research Shows
Measuring LLMs’ Ability to Perform Cryptanalysis
Here’s what Anthropic found when it turned Mythos loose on encryption algorithms
Stronger AI Safety Requires Peeking Inside the 'Black Box'
Claude Mythos degrades HAWK and developed new exploit for round-reduced AES
Kalla eftir inngripi stjórnvalda í gervigreindarkapphlaupið
AI-found bugs aren't proving any easier to exploit despite the hype
AI-assisted security tools are finding more bugs, but the threat level has not changed
VERITAS project could change the way scientists secure AI
Escape Artists: 'Incorrigible' AI Models Resist Rehabilitation
What Endpoint Security Actually Controls
Inside the OpenAI – Hugging Face Incident: The AI Breach With No Human Attacker Behind It
What Happened Between OpenAI and Hugging Face?
Open Evaluation Framework for AI Pentesting Agents on Real-World Targets
AI models caught cheating in cybersecurity evaluations
Sol Searching | Can Frontier Models Tackle Autonomous Long-Horizon Malware Analysis?
AI's cheatin' heart will make you weep