Trading Inference-Time Compute for Adversarial Robustness

• URL: http://arxiv.org/abs/2501.18841v1
• Date: Fri, 31 Jan 2025 01:20:44 GMT
• Title: Trading Inference-Time Compute for Adversarial Robustness
• Authors: Wojciech Zaremba, Evgenia Nitishinskaya, Boaz Barak, Stephanie Lin, Sam Toyer, Yaodong Yu, Rachel Dias, Eric Wallace, Kai Xiao, Johannes Heidecke, Amelia Glaese,
• Abstract summary: We conduct experiments on the impact of increasing inference-time compute in reasoning models on their robustness to adversarial attacks.<n>We find that across a variety of attacks, increased inference-time compute leads to improved robustness.
• Score: 27.514612815314084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attacks. We find that across a variety of attacks, increased inference-time compute leads to improved robustness. In many cases (with important exceptions), the fraction of model samples where the attack succeeds tends to zero as the amount of test-time compute grows. We perform no adversarial training for the tasks we study, and we increase inference-time compute by simply allowing the models to spend more compute on reasoning, independently of the form of attack. Our results suggest that inference-time compute has the potential to improve adversarial robustness for Large Language Models. We also explore new attacks directed at reasoning models, as well as settings where inference-time compute does not improve reliability, and speculate on the reasons for these as well as ways to address them.

Related papers

• Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods [39.89239733570008]
  This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models. We find that non-reasoning models, even with an extremely high inference budget, still fall substantially behind reasoning models. For reasoning models, majority voting proves to be a robust inference strategy, generally competitive or outperforming other more sophisticated ITC methods.
  arXiv  Detail & Related papers  (2025-04-18T19:32:55Z)
• Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning [113.49074603075032]
  Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. We explore whether scaling with longer CoTs can indeed impair the reasoning performance of Large Language Models (LLMs) in certain domains.
  arXiv  Detail & Related papers  (2025-02-25T10:48:05Z)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision [120.40788744292739]
  We propose a two-player paradigm that separates the roles of reasoning and critique models. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time.
  arXiv  Detail & Related papers  (2024-11-25T17:11:54Z)
• A Cost-Aware Approach to Adversarial Robustness in Neural Networks [1.622320874892682]
  We propose using accelerated failure time models to measure the effect of hardware choice, batch size, number of epochs, and test-set accuracy. We evaluate several GPU types and use the Tree Parzen Estimator to maximize model robustness and minimize model run-time simultaneously.
  arXiv  Detail & Related papers  (2024-09-11T20:43:59Z)
• A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE) [1.622320874892682]
  This work addresses the problem of understanding and predicting how particular model hyper- parameters influence the performance of a model in the presence of an adversary. The proposed approach uses survival models, worst-case examples, and a cost-aware analysis to precisely and accurately reject a particular model change. Using the proposed methodology, we show that ResNet is hopelessly against even the simplest of white box attacks.
  arXiv  Detail & Related papers  (2024-01-24T19:12:37Z)
• Generating Less Certain Adversarial Examples Improves Robust Generalization [22.00283527210342]
  This paper revisits the robust overfitting phenomenon of adversarial training.<n>We argue that overconfidence in predicting adversarial examples is a potential cause.<n>We propose a formal definition of adversarial certainty that captures the variance of the model's predicted logits on adversarial examples.
  arXiv  Detail & Related papers  (2023-10-06T19:06:13Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Re-thinking Data Availablity Attacks Against Deep Neural Networks [53.64624167867274]
  In this paper, we re-examine the concept of unlearnable examples and discern that the existing robust error-minimizing noise presents an inaccurate optimization objective. We introduce a novel optimization paradigm that yields improved protection results with reduced computational time requirements.
  arXiv  Detail & Related papers  (2023-05-18T04:03:51Z)
• On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach [42.81632484264218]
  In machine learning models, perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy. This paper aims to implement a novel hash-based ensemble approach that protects random forest against untargeted, random poisoning attacks.
  arXiv  Detail & Related papers  (2022-09-28T11:41:38Z)
• Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries [69.53730499849023]
  We show that adversarial examples can be successfully transferred to another independently trained model to induce prediction errors. We propose a deep learning-based pre-processing mechanism, which we refer to as a robust transferable feature extractor (RTFE)
  arXiv  Detail & Related papers  (2022-09-14T21:09:34Z)
• Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms [17.75675910162935]
  A new attack pattern negatively impacts the forecasting of a target time series. We develop two defense strategies to mitigate the impact of such attack. Experiments on real-world datasets confirm that our attack schemes are powerful.
  arXiv  Detail & Related papers  (2022-07-19T22:00:41Z)
• Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness [53.094682754683255]
  We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically. Our method learns the in adversarial attacks parameterized by a recurrent neural network. We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
  arXiv  Detail & Related papers  (2021-10-13T13:54:24Z)
• Double Robust Representation Learning for Counterfactual Prediction [68.78210173955001]
  We propose a novel scalable method to learn double-robust representations for counterfactual predictions. We make robust and efficient counterfactual predictions for both individual and average treatment effects. The algorithm shows competitive performance with the state-of-the-art on real world and synthetic data.
  arXiv  Detail & Related papers  (2020-10-15T16:39:26Z)
• Causal Modeling with Stochastic Confounders [11.881081802491183]
  This work extends causal inference with confounders. We propose a new approach to variational estimation for causal inference based on a representer theorem with a random input space.
  arXiv  Detail & Related papers  (2020-04-24T00:34:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.