Many-shot jailbreaking
•
5
Vlad Bogolin
vladbogo
AI & ML interests
LLMs, Computer Vision
Recent Activity
updated
a collection
2 days ago
AI Paper of the Day
upvoted
a
paper
2 days ago
Alignment faking in large language models
updated
a collection
3 days ago
AI Paper of the Day
Articles
Organizations
Posts
26
Post
2292
SwapAnything is a new method that allows swapping any object in an image with personalized concepts given by a reference image.
Key points:
1️⃣ It uses pre-trained diffusion models to enable precise and high-fidelity object swapping in images.
2️⃣Targeted variable swapping ensures perfect background preservation while swapping specific areas.
3️⃣SwapAnything achieves good results in single-object, multi-object, partial-object, and cross-domain swapping tasks.
Paper: SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing (2404.05717)
Project page: https://swap-anything.github.io
Congrats to the authors for their work!
Key points:
1️⃣ It uses pre-trained diffusion models to enable precise and high-fidelity object swapping in images.
2️⃣Targeted variable swapping ensures perfect background preservation while swapping specific areas.
3️⃣SwapAnything achieves good results in single-object, multi-object, partial-object, and cross-domain swapping tasks.
Paper: SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing (2404.05717)
Project page: https://swap-anything.github.io
Congrats to the authors for their work!
Post
1777
Anthropic introduces "Many-shot Jailbreaking" (MSJ), a new attack on large language models! MSJ exploits long context windows to override safety constraints.
Key Points:
* Prompts LLMs with hundreds of examples of harmful behavior formatted as a dialogue
* Generates malicious examples using an uninhibited "helpful-only" model
* Effective at jailbreaking models like Claude 2.0, GPT-3.5, GPT-4
* Standard alignment techniques provide limited protection against long context attacks
Paper: https://www.anthropic.com/research/many-shot-jailbreaking
More details in my blog: https://huggingface.co/blog/vladbogo/many-shot-jailbreaking
Congrats to the authors for their work!
Key Points:
* Prompts LLMs with hundreds of examples of harmful behavior formatted as a dialogue
* Generates malicious examples using an uninhibited "helpful-only" model
* Effective at jailbreaking models like Claude 2.0, GPT-3.5, GPT-4
* Standard alignment techniques provide limited protection against long context attacks
Paper: https://www.anthropic.com/research/many-shot-jailbreaking
More details in my blog: https://huggingface.co/blog/vladbogo/many-shot-jailbreaking
Congrats to the authors for their work!
Collections
5
A collection of papers that I think are interesting, one added each day
-
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 21 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 82 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 145 -
SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity
Paper • 2401.17072 • Published • 25
spaces
1
models
None public yet
datasets
None public yet