{"list":"other","total":51,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2309.07875","title":"Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions","created":"2023-09-14","cited_by_count":387},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243},{"id":"2311.05553","title":"Removing RLHF Protections in GPT-4 via Fine-Tuning","created":"2023-11-09","cited_by_count":171},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134},{"id":"2405.16833","title":"Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models","created":"2024-05-27","cited_by_count":125},{"id":"2006.12557","title":"Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks","created":"2020-06-22","cited_by_count":116},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96},{"id":"1804.07933","title":"Is feature selection secure against training data poisoning?","created":"2018-04-21","cited_by_count":93},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88},{"id":"1608.08182","title":"Data Poisoning Attacks on Factorization-Based Collaborative Filtering","created":"2016-08-29","cited_by_count":83},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52},{"id":"2402.06659","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","created":"2024-02-05","cited_by_count":50},{"id":"2412.12497","title":"NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning","created":"2024-12-17","cited_by_count":37},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33},{"id":"2402.14968","title":"Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment","created":"2024-02-22","cited_by_count":31},{"id":"2210.09671","title":"Not All Poisons are Created Equal: Robust Training against Data Poisoning","created":"2022-10-18","cited_by_count":30},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22},{"id":"1811.09982","title":"Is Data Clustering in Adversarial Settings Secure?","created":"2018-11-25","cited_by_count":18},{"id":"2410.15821","title":"The effect of fine-tuning on language model toxicity","created":"2024-10-21","cited_by_count":16},{"id":"2302.03684","title":"Temporal Robustness against Data Poisoning","created":"2023-02-07","cited_by_count":10},{"id":"2502.14828","title":"Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs","created":"2025-02-20","cited_by_count":10},{"id":"2412.02159","title":"Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach","created":"2024-12-03","cited_by_count":6},{"id":"2310.05141","title":"Transferable Availability Poisoning Attacks","created":"2023-10-08","cited_by_count":5},{"id":"2403.11981","title":"Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising","created":"2024-03-18","cited_by_count":1}],"next_cursor":null}