Trading Inference-Time Compute for Adversarial Robustness
OpenAI published research exploring the trade-off between inference-time compute and adversarial robustness. The work investigates whether allocating more compute at inference time can improve a model's resistance to adversarial attacks. This connects to the broader trend of using test-time compute scaling as a lever for capability and safety improvements.
Related guides (4)
Related events (8)
Computational limitations in robust classification and win-win results
OpenAI published research examining computational limitations in robust classification, exploring theoretical bounds on adversarially robust machine learning. The work investigates so-called 'win-win' results where both standard and robust accuracy can be achieved simultaneously. This is a foundational safety and robustness research contribution from 2019, addressing hardness results in adversarial ML.
Testing Robustness Against Unforeseen Adversaries
OpenAI published a method to evaluate whether neural network classifiers can defend against adversarial attacks not encountered during training. The approach introduces a new metric called UAR (Unforeseen Attack Robustness) to quantify a model's resilience to unanticipated attacks. The work argues for measuring robustness across a broader, more diverse set of attack types rather than only those seen in training.
Transfer of Adversarial Robustness Between Perturbation Types
OpenAI published research examining whether adversarial robustness trained against one type of perturbation (e.g., L-infinity) transfers to other perturbation types (e.g., L2, L1). The work investigates the generalization properties of adversarial training across different threat models. This is an early safety and robustness research contribution from OpenAI predating the modern LLM era.
AI and Compute: OpenAI Analysis of Exponential Growth in Training Compute Since 2012
OpenAI published an analysis in May 2018 showing that compute used in the largest AI training runs has been doubling every 3.4 months since 2012, far outpacing Moore's Law's 2-year doubling period. Over the 2012–2018 period, this metric grew by more than 300,000x. The analysis frames compute scaling as a key driver of AI progress and argues for preparing for systems with capabilities well beyond those of the time.
How to Train Your Model Dynamically Using Adversarial Data
This Hugging Face blog post describes a methodology for dynamically training models using adversarial data, likely in the context of improving robustness against adversarial examples. The post covers techniques for generating and incorporating adversarial inputs during the training loop to improve model resilience. Published in mid-2022, it targets practitioners looking to harden ML models against distribution shift and adversarial attacks.
Distributionally robust optimization framework for probabilistic runtime verification of AI agents
A new arXiv preprint introduces a sound and efficient framework for verifying probabilistic security policies for AI agents operating in complex digital environments, addressing limitations of prior Datalog-based approaches that assumed deterministic policies or predicate independence. The method uses distributionally robust optimization to compute sound upper bounds on policy violation probability without requiring independence assumptions between predicates. Evaluated on benchmarks for terminal and tool-calling agents, the approach outperforms prior art on the security-utility trade-off.
Adaptive asymmetric token compression accelerates time series language models up to 7.68×
A new arXiv preprint proposes an adaptive token budgeting framework for time series (TS) language models that compresses TS tokens using frequency-domain structure and progressively prunes prompt tokens across model layers. The authors demonstrate up to 7.68× inference acceleration with performance improvements in 78% of evaluated settings across forecasting, classification, imputation, and anomaly detection tasks. The work is motivated by the observation that TS tokens have uneven spectral contributions and prompt-token influence attenuates with model depth, making uniform token processing wasteful.
[AINews] The Inference Inflection
A Latent Space commentary piece reflecting on the broader implications of the 'inference age' in AI. The piece appears to be a daily AI news digest framing inference-time compute as a significant structural shift. Published during a relatively quiet news day, it offers analytical perspective on inference economics and deployment patterns rather than breaking news.