Prompt Injection Defenses Against LLM Cyberattacks
Interesting research: “Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks“: Large language models (LLMs) are increasingly…
Security
Subverting LLM Coders
Really interesting research: “An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection“: Abstract: Large…
AI-Powered APIs: Expanding Capabilities and Attack Surfaces
AI and APIs have a symbiotic relationship. APIs power AI by providing the necessary data and functionality, while AI enhances…
Jane Goodall: Reasons for hope | Starmus highlights
The trailblazing scientist shares her reasons for hope in the fight against climate change and how we can tackle seemingly…
IoT Devices in Password-Spraying Botnet
Microsoft is warning Azure cloud users that a Chinese controlled botnet is engaging in “highly evasive” password spraying. Not sure…
AIs Discovering Vulnerabilities
I’ve been writing about the possibility of AIs automatically discovering code vulnerabilities since at least 2018. This is an ongoing…
Nigerian man Sentenced to 26+ years in real estate phishing scams
Nigerian Kolade Ojelade gets 26 years in U.S. for phishing scams that stole millions by hacking email accounts. A Nigerian…
Sophos Versus the Chinese Hackers
Really interesting story of Sophos’s five-year war against Chinese hackers.
Attackers Abuse DocuSign API to Send Authentic-Looking Invoices At Scale
In a concerning trend, cybercriminals are leveraging DocuSign’s APIs to send fake invoices that appear strikingly authentic. Unlike traditional phishing…
Cybersecurity in Healthcare: Protecting Patient Data and Trust
Healthcare has taken center stage in cybercriminals’ crosshairs. Hospitals, clinics, and health systems are brimming with sensitive patient data that’s…