GPT-4o-mini Falls for Psychological Manipulation

Interesting experiment: To design their experiment, the University of Pennsylvania researchers tested 2024's GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. The researchers created experimental prompts...

Can We End the Cat-And-Mouse Game? Simulating Self-Evolving Phishing Attacks with LLMs and Genetic Algorithms

Anticipating emerging attack methodologies is crucial for proactive cybersecurity. Recent advances in Large Language Models LLMs have enabled the automated generation of phishing messages and accelerated research into potential attack techniques. However, predicting future threats remains...

PRISON: Unmasking the Criminal Potential of Large Language Models

As large language models LLMs advance, concerns about their misconduct in complex social contexts intensify. Existing research overlooked the systematic understanding and assessment of their criminal capability in realistic interactions. We propose a unified framework PRISON, to quantify LLMs'...

Cybersecurity’s next fight: How to protect employees from online harassment

The security community is continuously changing, growing, and learning from each other to better position the world against cyber threats. In the latest Voice of the Community blog series post, Microsoft Product Marketing Manager Natalia Godyla talks with Leigh Honeywell, CEO and Co-founder of Ta...

Cybersecurity’s next fight: How to protect employees from online harassment

The security community is continuously changing, growing, and learning from each other to better position the world against cyber threats. In the latest Voice of the Community blog series post, Microsoft Product Marketing Manager Natalia Godyla talks with Leigh Honeywell, CEO and Co-founder of Ta...

Details of a Computer Banking Scam

This is a longish video that describes a profitable computer banking scam thats run out of call centers in places like India. Theres a lot of fluff about glitterbombs and the like, but the details are interesting. The scammers convince the victims to give them remote access to their computers, an...

Social Engineering — Free Online Training for Hackers

For most of us Hacking is Technological in Nature. But, we usually forget the most important element of hacking that makes a successful hack from 10% to over 90%... ...The Human Element. And here the Social Engineering comes in. Social Engineering deals with non-technical kind of intrusion and...

Phishing Google Users with the Help of Google !

Phishing Google Users with the Help of Google ! How Hackers are phishing Gmail/Google users successfully ? Christy Philip Mathew, an Information Security Instructor from India shared a perfect trick with us. He just exploit human psychology. Lets see how: He Created a phishing Page of Google and...