research
173 articles with this tag
INFO
HIGH
INFO
INFO
INFO
INFO
INFO
INFO
CRITICAL
INFO
INFO
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
INFO
LOW
INFO
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
HIGH
INFO
INFO
INFO
INFO
INFO
MEDIUM
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
INFO
HIGH
LOW
INFO
INFO
INFO
INFO
MEDIUM
INFO
INFO
LOW
MEDIUM
Factoring "short-sleeve" RSA keys with polynomials
Prompt injection breaks today’s AI agents, study warns
AI is exposing the biggest weakness in cybersecurity: We never built a health model. Until now!
LABScon25 Replay | Keynote: Steps to an Ecology of Cyber
Bug bounties in the Mythos era
Smashing Security podcast #471: This AI worm just rewrote its own rules
Anthropic’s Claude Fable 5 is out for public use, with safeguards for high-risk requests
AI red teaming comes of age
Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models
Oculis hefur lykilrannsókn á augndropa við augnþurrki
Anthropic’s Project Glasswing Update
EDRChoker: Choking The Telemetry Stream to Bypass Defenses
Þróa nýja tegund bóluefnis með hjálp gervigreindar
Vilja hægja á gervigreindarkapphlaupinu
Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us
Bend the beam like Beckham to defeat anti-jamming tech
Microsoft Tries to Calm Legal Threat Fears After Zero-Day Disclosure Backlash
Two New Reports Offer Competing Explanations for Cybersecurity’s Growing Crisis
Nvidia and Microsoft Researchers Say AI Agents Don't Care About Safety or Reliability
Wardriving assessment across Mexico: Preparing for the 2026 World Cup
Pointing a Cursor at evading detection
This AI model backdoor attack stays hidden until you customize the model
Anthropic to Open Mythos AI to EU's ENISA
New Study Reveals the Manipulative ‘Dark Patterns’ of AI Chatbots
Websites can spy on user activity by analyzing SSD behavior
CrowdStrike Named a Leader in the First-Ever Gartner® Magic Quadrant™ for Cyberthreat Intelligence Technologies
CrowdStrike Named a Leader in the First-Ever Gartner® Magic Quadrant™ for Cyberthreat Intelligence Technologies
Identifying People Using Wi-Fi Routers
Anthropic to release Mythos-class models to the public
Prompt Injection finally broke my brain a little. My first article as a security student.
Meet Fractal, an OS made for microarchitecture reverse engineering
Researchers left AI agents alone in a virtual town and watched it all unravel
The readiness paradox: Why a false sense of cyber confidence is becoming a liability
Most dark web activity revolves around a handful of topics
AI red teaming agents change how LLMs get tested
Securing the gaming culture of cultures
On AI Security
Tune In: The Future of AI-Powered Vulnerability Discovery
AI cyberattackers are getting better faster
I Built an AI Cybersecurity Research Factory (for CTFs & Vulnerabilities)
Project Glasswing: what Mythos showed us
Autonomous AI Penetration Testing with Consent-First Ethical Framework — Research Paper + Working Implementation
The AI backdoor your security stack is not built to see
AI shrinks vulnerability exploitation window to hours
Deepfake detection is losing ground to generative models
Microsoft details new AI system for vulnerability discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
AI models are getting better at replacing cybersecurity pros on certain tasks
Vector embedding security gap exposes enterprise AI pipelines
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Researchers open-source a Wi-Fi cyber range for security training
Gervigreind: Árangur, áhætta og stefnumörkun
AI Vulnerability Research and the Fuzzer Era Déjà Vu
LLMs and Text-in-Text Steganography
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Mythos, MOAK, CTEM and the End of CVE Chasing
Autonomous Vulnerability Hunting with MCP
Tune In: The Future of AI-Powered Vulnerability Discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Segja augljósan bata í humarstofninum
Tune In: The Future of AI-Powered Vulnerability Discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Tune In: The Future of AI-Powered Vulnerability Discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Tune In: The Future of AI-Powered Vulnerability Discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Tune In: The Future of AI-Powered Vulnerability Discovery
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
CrowdStrike Technical Risk Assessments Reveal Common Exposure Patterns
Þróar frumlyf gegn alvarlegum fylgikvillum meðferðar
Can your coding style predict whether your code is vulnerable?
'Nature' Retracts Paper on the Benefits of ChatGPT in Education
What researchers learned about building an LLM security workflow
Tune In: The Future of AI-Powered Vulnerability Discovery
GPT-5.5 matches heavily hyped Mythos Preview in new cybersecurity tests
Everyone’s building AI agents. Almost nobody’s ready for what they do to identity.
Researchers move in the right direction, develop powerful GPS interference alarm
AI prompt confidentiality and false citations worry researchers
Italy moves to extradite Chinese national to U.S. over alleged COVID-19 research hacks
The Bot Left a Fingerprint: Detecting and Attributing LLM-Generated Passwords
What Anthropic’s Mythos Means for the Future of Cybersecurity
Proofpoint Research Reveals Half of Global Organizations Experienced AI Incidents Despite Having AI Security Controls in Place
DeepZero - Automated Vulnerability Research
Study Finds A Third of New Websites are AI-Generated
Thinking Outside The Box: New Attack Surfaces in Sandboxed AI Agents
Þrjú hundruð krítískir veikleikar
Why Anthropic was right to form Project Glasswing
Lax á kókaíni syndir linnulaust
With AI’s help, North Korean hackers stumbled into a near-undetectable attack