Image de couverture de livre

Automated Adversarial Discovery for Safety Classifiers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lal, Yash Kumar, Lahoti, Preethi, Sinha, Aradhana, Qin, Yao, Balashankar, Ananth
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Inducing Group Fairness in Prompt-Based Language Model Decisions
par: Atwood, James, et autres
Publié: (2024)

Adversarial Reinforcement Learning for Large Language Model Agent Safety
par: Wang, Zizhao, et autres
Publié: (2025)

BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
par: Huang, Baichuan, et autres
Publié: (2025)

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
par: Wu, Zhaofeng, et autres
Publié: (2024)

Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation
par: Shen, Minghe, et autres
Publié: (2026)

InfAlign: Inference-aware language model alignment
par: Balashankar, Ananth, et autres
Publié: (2024)

ISO-Bench: Benchmarking Multimodal Causal Reasoning in Visual-Language Models through Procedural Plans
par: Sadana, Ananya, et autres
Publié: (2025)

BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection
par: Gupta, Atharva, et autres
Publié: (2026)

Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks
par: Sinha, Aradhana, et autres
Publié: (2023)

Gujarati-English Code-Switching Speech Recognition using ensemble prediction of spoken language
par: Sharma, Yash, et autres
Publié: (2024)

Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
par: Patil, Parth, et autres
Publié: (2026)

CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans
par: Lal, Yash Kumar, et autres
Publié: (2024)

Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics
par: Kumar, Sanjeev, et autres
Publié: (2026)

SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks
par: Dey, Gourab, et autres
Publié: (2024)

Set-Theoretic Compositionality of Sentence Embeddings
par: Bansal, Naman, et autres
Publié: (2025)

Measuring Representation Robustness in Large Language Models for Geometry
par: Jawandhia, Vedant, et autres
Publié: (2026)

MuSciClaims: Multimodal Scientific Claim Verification
par: Lal, Yash Kumar, et autres
Publié: (2025)

Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
par: Lal, Yash Kumar, et autres
Publié: (2023)

XITE: Cross-lingual Interpolation for Transfer using Embeddings
par: Fazili, Barah, et autres
Publié: (2026)

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
par: Sinha, Yash, et autres
Publié: (2024)

A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers
par: Roth, Tom, et autres
Publié: (2024)

Can Stories Help LLMs Reason? Curating Information Space Through Narrative
par: Javadi, Vahid Sadiri, et autres
Publié: (2024)

A Generative Adversarial Attack for Multilingual Text Classifiers
par: Roth, Tom, et autres
Publié: (2024)

Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
par: Sturman, Olivia, et autres
Publié: (2024)

Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change
par: Hariharan, Ananth, et autres
Publié: (2025)

The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
par: Sahoo, Devanshu, et autres
Publié: (2026)

Boundary-targeted Membership Inference Attacks on Safety Classifiers
par: Hughes, Anthony, et autres
Publié: (2026)

Towards More Realistic Extraction Attacks: An Adversarial Perspective
par: More, Yash, et autres
Publié: (2024)

SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking
par: Zhu, Xiangyang, et autres
Publié: (2025)

LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers
par: Ghosh, Shantanu, et autres
Publié: (2024)

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
par: Chehbouni, Khaoula, et autres
Publié: (2024)

CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs
par: Chen, Sijia, et autres
Publié: (2025)

Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning
par: Agrawal, Ashish Sunil, et autres
Publié: (2024)

Aviation Safety Enhancement via NLP & Deep Learning: Classifying Flight Phases in ATSB Safety Reports
par: Nanyonga, Aziida, et autres
Publié: (2025)

Certifying LLM Safety against Adversarial Prompting
par: Kumar, Aounon, et autres
Publié: (2023)

Model Editing with Graph-Based External Memory
par: Atri, Yash Kumar, et autres
Publié: (2025)

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
par: Muppidi, Ananth, et autres
Publié: (2025)

TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation
par: Chandra, Joydeep, et autres
Publié: (2026)

LexGen: Domain-aware Multilingual Lexicon Generation
par: Maheshwari, Ayush, et autres
Publié: (2024)

Automated Statistical Model Discovery with Language Models
par: Li, Michael Y., et autres
Publié: (2024)