Alternatives and similar repositories for shallow-vs-deep-alignment:

Users that are interested in shallow-vs-deep-alignment are comparing it to the libraries listed below

• princeton-nlp / benign-data-breaks-safety
  ☆23Updated 2 months ago
• boyiwei / alignment-attribution-code
  Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆62Updated 2 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆58Updated last month
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆47Updated 3 months ago
• UCSC-VLAA / vllm-safety-benchmark
  [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
  ☆72Updated last year
• ejones313 / auditing-llms
  ☆49Updated last year
• swj0419 / muse_bench
  ☆18Updated 5 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆39Updated last year
• ChenWu98 / agent-attack
  [Arxiv 2024] Adversarial attacks on multimodal agents
  ☆44Updated 5 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆48Updated 2 months ago
• SORRY-Bench / sorry-bench
  SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
  ☆34Updated 5 months ago
• sail-sg / closer-look-LLM-unlearning
  The official code of the paper "A Closer Look at Machine Unlearning for Large Language Models".
  ☆18Updated last week
• Improbable-AI / curiosity_redteam
  Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…
  ☆66Updated 9 months ago
• zhxieml / remiss-jailbreak
  ☆21Updated 5 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆85Updated 6 months ago
• OPTML-Group / SOUL
  Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
  ☆14Updated 2 months ago
• licong-lin / negative-preference-optimization
  ☆40Updated 5 months ago
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆26Updated last month
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆36Updated last month
• chujiezheng / LLM-Safeguard
  Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
  ☆78Updated 3 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆52Updated 4 months ago
• sail-sg / Attention-Sink
  [ATTRIB @ NeurIPS 2024 Oral] When Attention Sink Emerges in Language Models: An Empirical View
  ☆36Updated 2 months ago
• ChnQ / TracingLLM
  ☆24Updated 6 months ago
• zhaoyiran924 / Probe-Sampling
  [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
  ☆20Updated last month
• yuplin2333 / representation-space-jailbreak
  Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…
  ☆14Updated 4 months ago
• abhishekpanigrahi1996 / Skill-Localization-by-grafting
  ☆47Updated 11 months ago
• VITA-Group / Robust_Weight_Signatures
  [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
  ☆15Updated last year
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆19Updated last year
• locuslab / tofu
  Landing Page for TOFU
  ☆103Updated 6 months ago
• renqibing / CodeAttack
  [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
  ☆30Updated last month