Imagen de Portada

Can Go AIs be adversarially robust?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tseng, Tom, McLean, Euan, Pelrine, Kellin, Wang, Tony T., Gleave, Adam
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploiting Novel GPT-4 APIs
por: Pelrine, Kellin, et al.
Publicado: (2023)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
por: Struppek, Lukas, et al.
Publicado: (2026)

Scaling Trends for Data Poisoning in LLMs
por: Bowen, Dillon, et al.
Publicado: (2024)

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
por: Kowal, Matthew, et al.
Publicado: (2026)

Language models are better than humans at next-token prediction
por: Shlegeris, Buck, et al.
Publicado: (2022)

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
por: Murphy, Brendan, et al.
Publicado: (2025)

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
por: Pandey, Punya Syon, et al.
Publicado: (2025)

Preference Learning with Lie Detectors can Induce Honesty or Evasion
por: Cundy, Chris, et al.
Publicado: (2025)

A Systematic Investigation of The RL-Jailbreaker in LLMs
por: Mohammedalamen, Montaser, et al.
Publicado: (2026)

The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
por: Taufeeque, Mohammad, et al.
Publicado: (2026)

Enhancing robustness of data-driven SHM models: adversarial training with circle loss
por: Yang, Xiangli, et al.
Publicado: (2024)

RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
por: Song, Jialei, et al.
Publicado: (2025)

Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN
por: Taufeeque, Mohammad, et al.
Publicado: (2025)

Multi-Task Reinforcement Learning Enables Parameter Scaling
por: McLean, Reginald, et al.
Publicado: (2025)

Curvature Dynamic Black-box Attack: revisiting adversarial robustness via dynamic curvature estimation
por: Sun, Peiran
Publicado: (2025)

Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
por: Black, James R. M., et al.
Publicado: (2025)

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
por: Bowen, Dillon, et al.
Publicado: (2025)

Scaling Trends in Language Model Robustness
por: Howe, Nikolaus, et al.
Publicado: (2024)

STARC: A General Framework For Quantifying Differences Between Reward Functions
por: Skalse, Joar, et al.
Publicado: (2023)

MXNorm: Reusing MXFP block scales for efficient tensor normalisation
por: McLean, Callum, et al.
Publicado: (2026)

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness
por: Ballarin, Emanuele, et al.
Publicado: (2023)

$\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning
por: Kläser, Kerstin, et al.
Publicado: (2024)

FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detection
por: Lunghi, Daniele, et al.
Publicado: (2025)

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
por: Lang, Leon, et al.
Publicado: (2024)

It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics
por: Kowal, Matthew, et al.
Publicado: (2025)

Planning in a recurrent neural network that plays Sokoban
por: Taufeeque, Mohammad, et al.
Publicado: (2024)

Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG
por: Guo, Manshan, et al.
Publicado: (2024)

NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative model
por: Xie, Xinheng, et al.
Publicado: (2024)

Large language models can effectively convince people to believe conspiracies
por: Costello, Thomas H., et al.
Publicado: (2026)

Evaluating the robustness of adversarial defenses in malware detection systems
por: Jafari, Mostafa, et al.
Publicado: (2025)

Deep MMD Gradient Flow without adversarial training
por: Galashov, Alexandre, et al.
Publicado: (2024)

Robust NAS under adversarial training: benchmark, theory, and beyond
por: Wu, Yongtao, et al.
Publicado: (2024)

Missing value imputation with adversarial random forests -- MissARF
por: Golchian, Pegah, et al.
Publicado: (2025)

Fixed-point graph convolutional networks against adversarial attacks
por: Khan, Shakib, et al.
Publicado: (2025)

Meta-World+: An Improved, Standardized, RL Benchmark
por: McLean, Reginald, et al.
Publicado: (2025)

Deep generative models as an adversarial attack strategy for tabular machine learning
por: Dyrmishi, Salijona, et al.
Publicado: (2024)

Properties that allow or prohibit transferability of adversarial attacks among quantized networks
por: Shrestha, Abhishek, et al.
Publicado: (2024)

How adversarial attacks can disrupt seemingly stable accurate classifiers
por: Sutton, Oliver J., et al.
Publicado: (2023)

Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
por: Rivera, Mauricio, et al.
Publicado: (2024)

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
por: Mazeika, Mantas, et al.
Publicado: (2025)