paper

an archive of posts with this tag

May 30, 2026 Tamper-Resistant Safeguards (TAR) — Fine-tuning 자체에 견디는 safety
May 29, 2026 Circuit Breakers — 유해 representation을 incoherent state로 리라우팅
May 29, 2026 Emergent Misalignment — 안전한 코드 학습이 모델을 전반적으로 나쁘게 만든다
May 29, 2026 Shallow Safety Alignment — RLHF는 첫 5개 토큰만 reshape한다
May 29, 2026 Exploiting Novel GPT-4 APIs — 세 가지 공격 표면을 한 번에 점검하기
May 29, 2026 Covert Malicious Finetuning — 학습 데이터가 모두 무해해 보이는 공격
May 29, 2026 Universal Jailbreak Backdoors from Poisoned RLHF — 트리거 단어 하나가 'sudo'가 된다
May 29, 2026 LoRA Undoes Safety — QLoRA로 Llama-2-70B-Chat의 거부율을 1%로
May 29, 2026 Removing RLHF Protections in GPT-4 via Fine-Tuning — 340예시로 frontier API 깨기
May 29, 2026 Shadow Alignment — 100개 QA + 1 GPU-시간으로 open-weight 5종 깨기
May 29, 2026 Fine-tuning Compromises Safety — 10개 예시면 alignment가 무너진다
May 29, 2026 Refusal Direction & Abliteration — 거부는 하나의 방향이다
May 29, 2026 PKU-SafeRLHF-30K: A Dual-Preference Dataset for Safe-RLHF
May 26, 2026 사이버 보안에서의 LLM: 공격·방어·평가의 지형
May 26, 2026 Claude Mythos와 사이버 보안 LLM: 자율 취약점 발견의 변곡점
May 26, 2026 Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
May 26, 2026 CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
May 26, 2026 AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
May 26, 2026 CAIBench: A Meta-Benchmark for Evaluating Cybersecurity AI Agents
May 26, 2026 CyberSecEval (1–3): Meta Purple Llama의 사이버 보안 위험·역량 평가
May 26, 2026 CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
May 26, 2026 SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity
May 26, 2026 ALMA: 9,000개 주석만으로 LLM을 정렬하기
May 26, 2026 PIKA: 난이도에 집중한 expert-level 합성 정렬 데이터셋
May 26, 2026 WildJailbreak: in-the-wild 탈옥을 대규모로 합성한 안전 학습 데이터셋
May 26, 2026 BeaverTails: helpfulness와 harmlessness를 분리한 안전 정렬 데이터셋
May 26, 2026 HarmfulQA & RED-INSTRUCT: Chain of Utterances로 유해 질문을 만들고 안전 정렬까지
May 26, 2026 HH-RLHF Red-Team Attempts: Anthropic의 38,961건 레드팀 대화 데이터셋
May 26, 2026 AdvBench: LLM 공격 평가의 사실상 표준이 된 유해 행동 데이터셋
May 25, 2026 에이전트란 무엇인가: 지능형 에이전트의 고전 정의부터 LLM 에이전트까지
May 25, 2026 AgentBench: Evaluating LLMs as Agents
May 25, 2026 GAIA: a benchmark for General AI Assistants
May 25, 2026 SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
May 25, 2026 TravelPlanner: A Benchmark for Real-World Planning with Language Agents
May 25, 2026 MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
May 25, 2026 OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
May 18, 2026 Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
May 18, 2026 Constitutional AI: Harmlessness from AI Feedback
May 18, 2026 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
May 18, 2026 HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
May 16, 2026 AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
May 16, 2026 InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
May 16, 2026 AgenticRed: Evolving Agentic Systems for Red-Teaming
May 16, 2026 Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
May 16, 2026 Curiosity-driven Red-teaming for Large Language Models
May 16, 2026 Many-shot Jailbreaking
May 16, 2026 Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
May 16, 2026 GPTFuzzer: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
May 16, 2026 Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
May 16, 2026 AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
May 16, 2026 Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
May 16, 2026 Red Teaming Language Models with Language Models
Apr 29, 2026 CodeAttack: Code-based Adversarial Attacks for Pre-trained Programming Language Models
Apr 29, 2026 Jailbreaking Black Box Large Language Models in Twenty Queries
Apr 29, 2026 Universal and Transferable Adversarial Attacks on Aligned Language Models
Apr 12, 2026 A.X K1 Technical Report
Apr 12, 2026 TelAgentBench: A Multi-faceted Benchmark for Evaluating LLM-based Agents in Telecommunications
Apr 11, 2026 TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models
Apr 11, 2026 FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
Apr 09, 2026 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Dec 28, 2024 LoRA vs Full Fine-tuning: An Illusion of Equivalence
Dec 11, 2024 Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method 설명
Sep 19, 2024 META-REWARDING LANGUAGE MODELS: Self-Improving Alignment with LLM-as-a-Meta-Judge 설명
Nov 19, 2023 What Makes Multi-modal Learning Better than Single (Provably)
Aug 06, 2023 FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Jun 28, 2023 TinyViT
Jun 28, 2023 EdgeViT
Jun 21, 2023 Integral Neural Network
Apr 29, 2023 Invariant Representation for Unsupervised Image Restoration
Apr 16, 2023 DINE: Domain Adaptation from Single and Multiple Black-box Predictors
Apr 16, 2023 MobileOne: An Improved One millisecond Mobile Backbone
Apr 08, 2023 Proper Reuse of Image Classification Features Improves Object Detection
Apr 01, 2023 Meta Pseudo Labels
Mar 29, 2023 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Mar 28, 2023 FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Mar 21, 2023 Cross-Domain Adaptive Teacher for Object Detection
Mar 14, 2023 Rethinking “Batch” in BatchNorm
Mar 07, 2023 Convolutional Character Network
Feb 18, 2023 Simple Baselines for Image Restoration
Jan 05, 2023 Bootstrap your own latent
May 09, 2022 FitNet
Jan 27, 2021 [AutoML] NASNet
Jan 10, 2021 학부생이 본 SENet
Jan 03, 2021 [네트워크 경량화] EfficientNet