Podcast

The podcast where we breakdown the recent AI papers and explain them in simple terms for you to understand.

Arxiv Paper – Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation – AI Breakdown

In this episode, we discuss Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation by Danny Halawi, Alexander Wei, Eric Wallace, Tony T. Wang, Nika Haghtalab, Jacob Steinhardt. The paper highlights security risks in black-box finetuning interfaces for large language models and introduces covert malicious finetuning, a method to compromise a model's safety undetected. This involves creating an innocuous-looking dataset that, collectively, trains the model to handle and produce harmful content. When tested on GPT-4, the method was able to execute harmful instructions 99% of the time while bypassing typical safety measures, underscoring the difficulty in safeguarding finetuning processes from advanced threats.

1. Arxiv Paper – Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation 03:24
2. Arxiv Paper – Video Instruction Tuning With Synthetic Data 04:19
3. Arxiv Paper – Generative Agent Simulations of 1,000 People 04:26
4. NeurIPS 2024 – Moving Off-the-Grid: Scene-Grounded Video Representations 04:59
5. Arxiv Paper – Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution 04:58

News

• Arxiv Paper – Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
  In this episode, we discuss Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation by Danny Halawi, Alexander Wei, Eric Wallace,… Read more: Arxiv Paper – Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
• Arxiv Paper – Video Instruction Tuning With Synthetic Data
  In this episode, we discuss Video Instruction Tuning With Synthetic Data by Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li,… Read more: Arxiv Paper – Video Instruction Tuning With Synthetic Data
• Arxiv Paper – Generative Agent Simulations of 1,000 People
  In this episode, we discuss Generative Agent Simulations of 1,000 People by Joon Sung Park, Carolyn Q. Zou, Aaron Shaw,… Read more: Arxiv Paper – Generative Agent Simulations of 1,000 People
• NeurIPS 2024 – Moving Off-the-Grid: Scene-Grounded Video Representations
  In this episode, we discuss Moving Off-the-Grid: Scene-Grounded Video Representations by Sjoerd van Steenkiste, Daniel Zoran, Yi Yang, Yulia Rubanova,… Read more: NeurIPS 2024 – Moving Off-the-Grid: Scene-Grounded Video Representations
• Arxiv Paper – Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution
  In this episode, we discuss Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution by Peng Wang, Shuai… Read more: Arxiv Paper – Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution