AI Risks

Ash Ganda

Oct 173 min read

The Ghost of Dehumanization in AI: A Critical Examination

Explore the challenges of implementing AI in society and how cognitive science can help combat dehumanizing aspects of AI technologies.

0 views0 comments

Ash Ganda

Oct 103 min read

Protecting Your Chatbot: Understanding the Threat of Indirect Prompt Injection in AI Systems Like ChatGPT

Indirect prompt injection attacks exploit the retrieval capabilities of LLM-integrated applications, allowing adversaries to cause damage.

1 view0 comments

Ash Ganda

Oct 14 min read

Navigating the Ethical and Legal Dimensions of AI in Safety-Critical Systems

This article explores the implications of AI in safety-critical systems through the lens of privacy, cybersecurity, algorithmic fairness.

0 views0 comments

Ash Ganda

Sep 305 min read

Big Brother's New Toy: AI in Surveillance—The Good, the Bad, and the Creepy

AI integration in surveillance systems, commonly seen in public spaces and workplaces, presents benefits and ethical concerns

8 views0 comments

Ash Ganda

Sep 202 min read

Understanding Poisoning Attacks and Countermeasures for Machine Learning

Poisoning attacks pose a real threat to machine learning systems and thus are a concern for the security community.

0 views0 comments

Ash Ganda

Sep 202 min read

Protecting Your AI Systems: Understanding the Risks of Prompt Injection Attacks in LLMs

LLMs face an emerging threat from prompt injection attack, that specifically target open AI systems.

5 views0 comments