Researchers Use Poetry to Jailbreak AI Models – Dark Reading
When prompts were presented in poetic rather than prose form, attack success rates increased from 8% to 43%, on average — a fivefold increase. – Read More
Dark Reading
New Raptor Framework Uses Agentic Workflows to Create Patches – Dark Reading
Researchers utilized prompts and large language models to develop an open-source AI framework capable of generating both vulnerability exploits and patches. – Read More
DPRK’s ‘Contagious Interview’ Spawns Malicious Npm Package Factory – Dark Reading
North Korean attackers have delivered more than 197 malicious packages with 31K-plus downloads since Oct. 10, as part of ongoing state-sponsored activity to compromise software developers. – Read More
Tomiris Unleashes ‘Havoc’ With New Tools, Tactics – Dark Reading
The Russian-speaking group is targeting government and diplomatic entities in CIS member states and Central Asia in its latest cyber-espionage campaign. – Read More
CodeRED Emergency Alert Platform Shut Down Following Cyberattack – Dark Reading
The Inc ransomware gang took responsibility for the attack earlier this month and claimed it stole sensitive subscriber data. – Read More
Police Disrupt ‘Cryptomixer,’ Seize Millions in Crypto – Dark Reading
Multiple European law enforcement agencies recently disrupted Cryptomixer, a service allegedly used by cybercriminals to launder ill-gotten gains from ransomware and other cyber activities. – Read More
Shai-hulud 2.0 Variant Threatens Cloud Ecosystem – Dark Reading
The latest attack from the self-replicating, npm-package poisoning worm can also steal credentials and secrets from AWS, Google Cloud Platform, and Azure. – Read More
Digital Fraud at Industrial Scale: 2025 Wasn’t Great – Dark Reading
Advanced fraud attacks surged 180% in 2025 as cyber-scammers used generative AI to churn out flawless IDs, deepfakes, and autonomous bots at levels never before seen. – Read More
‘Dark LLMs’ Aid Petty Criminals, But Underwhelm Technically – Dark Reading
As in the wider world, AI is not quite living up to the hype in the cyber underground. But it’s definitely helping low-level cybercriminals do competent work. – Read More
Prompt Injections Loom Large Over ChatGPT’s Atlas Browser – Dark Reading
It’s the law of unintended consequences: equipping browsers with agentic AI opens the door to an exponential volume of prompt injections. – Read More
How Malware Authors Are Incorporating LLMs to Evade Detection – Dark Reading
Cyberattackers are integrating large language models (LLMs) into the malware, running prompts at runtime to evade detection and augment their code on demand. – Read More
Enterprises Aren’t Confident They Can Secure Non-Human Identities (NHIs) – Dark Reading
More than half of organizations surveyed aren’t sure they can secure non-human identities (NHIs), underscoring the lag between the rollout of these identities and the tools to protect them. –…
Iran Exploits Cyber Domain to Aid Kinetic Strikes – Dark Reading
The country deploys “cyber-enabled kinetic targeting” prior to — and following — real-world missile attacks against ships and land-based targets. – Read More
Advanced Security Isn’t Stopping Ancient Phishing Tactics – Dark Reading
New research reveals that sophisticated phishing attacks consistently bypass traditional enterprise security measures. – Read More
Cheap Hardware Module Bypasses AMD, Intel Memory Encryption – Dark Reading
Researchers built an inexpensive device that circumvents chipmakers’ confidential computing protections and reveals weaknesses in scalable memory encryption. – Read More