tml-epfl/llm-adaptive-attacks

Issues

• Potential BUG

  #7 opened a month ago by Junjie-Chu
  1

• Questions about adversarial suffix generation

  #8 opened a month ago by Syyabb
  1

• get_universal_manual_prompt template

  #6 opened 2 months ago by wusuhuang
  2

• Question about the tokenizer's pad_token when using llama2 as target model

  #5 opened 2 months ago by Kris-Lcq
  2

• Reproducing the experimental results

  #4 opened 2 months ago by bxiong1
  10

• A typo in main.py

  #3 opened 5 months ago by franciscoliu
  1

• Question about the system prompt used for llama-2

  #2 opened 5 months ago by rickyang1114
  2

• How to obtain the adv_init?

  #1 opened 5 months ago by xszheng2020
  2