sail-sg / Cheating-LLM-Benchmarks

Related projects ⓘ

Alternatives and complementary repositories for Cheating-LLM-Benchmarks

• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆48Updated 3 months ago
• sail-sg / Attention-Sink
  [ATTRIB @ NeurIPS 2024] When Attention Sink Emerges in Language Models: An Empirical View
  ☆29Updated last month
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆84Updated 5 months ago
• decoding-comp-trust / comp-trust
  Codebase for decoding compressed trust.
  ☆20Updated 6 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆38Updated last year
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆28Updated 4 months ago
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆64Updated 8 months ago
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆17Updated 8 months ago
• locuslab / acr-memorization
  ☆26Updated 3 weeks ago
• ChenWu98 / agent-attack
  [Arxiv 2024] Adversarial attacks on multimodal agents
  ☆39Updated 4 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆10Updated 8 months ago
• weizeming / momentum-attack-llm
  ☆14Updated 6 months ago
• kztakemoto / simbaja
  All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks
  ☆14Updated 6 months ago
• sail-sg / D-TRAK
  Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
  ☆23Updated 9 months ago
• ejones313 / auditing-llms
  ☆49Updated last year
• azshue / AutoPoison
  The official repository of the paper "On the Exploitability of Instruction Tuning".
  ☆57Updated 9 months ago
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆21Updated 4 months ago
• zhxieml / remiss-jailbreak
  ☆20Updated 4 months ago
• renqibing / ActorAttack
  ☆50Updated 2 weeks ago
• thestephencasper / explore_establish_exploit_llms
  ☆31Updated last year
• sail-sg / dice
  Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
  ☆39Updated 3 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆21Updated last month
• peterljq / Parsimonious-Concept-Engineering
  Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
  ☆26Updated 2 weeks ago
• tml-epfl / llm-past-tense
  Does Refusal Training in LLMs Generalize to the Past Tense? [NeurIPS 2024 Safe Generative AI Workshop (Oral)]
  ☆57Updated last month
• yidingjiang / ado
  The repository contains code for Adaptive Data Optimization
  ☆18Updated last month
• locuslab / tofu
  Landing Page for TOFU
  ☆98Updated 5 months ago
• UCSC-VLAA / AttnGCG-attack
  ☆13Updated last month
• sail-sg / P-DoS
  [ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models
  ☆13Updated 3 weeks ago
• licong-lin / negative-preference-optimization
  ☆35Updated 4 months ago
• boyiwei / alignment-attribution-code
  Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆59Updated last month