arXiv subjects

Aleksander Mądry

Publications and source records attributed to Aleksander Mądry.

15 recordsLinked to original sources

arXiv2026

Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale

Personalization algorithms determine what content users encounter on online platforms. Auditing these systems is difficult because independent auditors have only black-box access to the algorithms, while personalization depends on users' attributes, behavior, and evolving interaction histories. Existing auditing methods face a tradeoff: studies with real users capture realistic behavior but are costly and hard to control, whereas sock-puppet audits scale more easily but often rely on scripted behavior that limits realism. Beyond this, both approaches struggle to decouple user attributes from user behavior, limiting our ability to causally understand personalization. To address this gap, we introduce a framework for black-box audits of personalization algorithms using generative AI agents as behavioral engines for synthetic accounts. Each agent is instantiated with a fixed persona, grounded in demographic and political survey data, and interacts with a platform's content by reasoning about it and choosing actions. Because behavior is fixed within each persona while platform-visible signals such as age, gender, or location can be experimentally perturbed, our design enables counterfactual auditing of how platforms respond to user attributes. As a case study, we deploy 1,120 agents on X shortly after the 2024 U.S. election, spanning 14 personas and three counterfactual conditions, collecting over 200,000 content exposures. We find that X's algorithmic feed amplifies toxic, polarizing, political, and right-leaning content relative to the chronological feed, with amplification varying sharply by user ideology. Counterfactual analyses show that demographic signals affect content delivery in persona-dependent ways: pooled effects are largely null, while subgroup-level effects vary in direction and magnitude. Our work establishes GenAI-based agents as a new tool for algorithmic auditing.

cs.CL↗

arXiv2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

cs.AI↗

arXiv2025

Large-Scale, Longitudinal Study of Large Language Models During the 2024 US Election Season

The 2024 US presidential election is the first major contest to occur in the US since the popularization of large language models (LLMs). Building on lessons from earlier shifts in media (most notably social media's well studied role in targeted messaging and political polarization) this moment raises urgent questions about how LLMs may shape the information ecosystem and influence political discourse. While platforms have announced some election safeguards, how well they work in practice remains unclear. Against this backdrop, we conduct a large-scale, longitudinal study of 12 models, queried using a structured survey with over 12,000 questions on a near-daily cadence from July through November 2024. Our design systematically varies content and format, resulting in a rich dataset that enables analyses of the models' behavior over time (e.g., across model updates), sensitivity to steering, responsiveness to instructions, and election-related knowledge and "beliefs." In the latter half of our work, we perform four analyses of the dataset that (i) study the longitudinal variation of model behavior during election season, (ii) illustrate the sensitivity of election-related responses to demographic steering, (iii) interrogate the models' beliefs about candidates' attributes, and (iv) reveal the models' implicit predictions of the election outcome. To facilitate future evaluations of LLMs in electoral contexts, we detail our methodology, from question generation to the querying pipeline and third-party tooling. We also publicly release our dataset at https://huggingface.co/datasets/sarahcen/llm-election-data-2024

cs.CY↗

arXiv2025

AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services

The widespread adoption of AI in recent years has led to the emergence of AI supply chains: complex networks of AI actors contributing models, datasets, and more to the development of AI products and services. AI supply chains have many implications yet are poorly understood. In this work, we take a first step toward a formal study of AI supply chains and their implications, providing two illustrative case studies indicating that both AI development and regulation are complicated in the presence of supply chains. We begin by presenting a brief historical perspective on AI supply chains, discussing how their rise reflects a longstanding shift towards specialization and outsourcing that signals the healthy growth of the AI industry. We then model AI supply chains as directed graphs and demonstrate the power of this abstraction by connecting examples of AI issues to graph properties. Finally, we examine two case studies in detail, providing theoretical and empirical results in both. In the first, we show that information passing (specifically, of explanations) along the AI supply chains is imperfect, which can result in misunderstandings that have real-world implications. In the second, we show that upstream design choices (e.g., by base model providers) have downstream consequences (e.g., on AI products fine-tuned on the base model). Together, our findings motivate further study of AI supply chains and their increasingly salient social, economic, regulatory, and technical implications.

cs.CY↗

arXiv2025

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering. To this end, we curate 75 ML engineering-related competitions from Kaggle, creating a diverse set of challenging tasks that test real-world ML engineering skills such as training models, preparing datasets, and running experiments. We establish human baselines for each competition using Kaggle's publicly available leaderboards. We use open-source agent scaffolds to evaluate several frontier language models on our benchmark, finding that the best-performing setup--OpenAI's o1-preview with AIDE scaffolding--achieves at least the level of a Kaggle bronze medal in 16.9% of competitions. In addition to our main results, we investigate various forms of resource scaling for AI agents and the impact of contamination from pre-training. We open-source our benchmark code (github.com/openai/mle-bench/) to facilitate future research in understanding the ML engineering capabilities of AI agents.

cs.CL↗

arXiv2024

GPT-4o System Card

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

cs.CL↗

arXiv2021

Faster Sparse Minimum Cost Flow by Electrical Flow Localization

We give an $\widetilde{O}({m^{3/2 - 1/762} \log (U+W))}$ time algorithm for minimum cost flow with capacities bounded by $U$ and costs bounded by $W$. For sparse graphs with general capacities, this is the first algorithm to improve over the $\widetilde{O}({m^{3/2} \log^{O(1)} (U+W)})$ running time obtained by an appropriate instantiation of an interior point method [Daitch-Spielman, 2008]. Our approach is extending the framework put forth in [Gao-Liu-Peng, 2021] for computing the maximum flow in graphs with large capacities and, in particular, demonstrates how to reduce the problem of computing an electrical flow with general demands to the same problem on a sublinear-sized set of vertices -- even if the demand is supported on the entire graph. Along the way, we develop new machinery to assess the importance of the graph's edges at each phase of the interior point method optimization process. This capability relies on establishing a new connections between the electrical flows arising inside that optimization process and vertex distances in the corresponding effective resistance metric.

cs.DS↗

arXiv2021

Certified Patch Robustness via Smoothed Vision Transformers

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We demonstrate how using vision transformers enables significantly better certified patch robustness that is also more computationally efficient and does not incur a substantial drop in standard accuracy. These improvements stem from the inherent ability of the vision transformer to gracefully handle largely masked images. Our code is available at https://github.com/MadryLab/smoothed-vit.

cs.CV↗

arXiv2021

Leveraging Sparse Linear Layers for Debuggable Deep Networks

We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantiatively via numerical and human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks. The code for our toolkit can be found at https://github.com/madrylab/debuggabledeepnetworks.

cs.LG↗

arXiv2020

Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs

We present an $m^{4/3+o(1)}\log W$-time algorithm for solving the minimum cost flow problem in graphs with unit capacity, where $W$ is the maximum absolute value of any edge weight. For sparse graphs, this improves over the best known running time for this problem and, by well-known reductions, also implies improved running times for the shortest path problem with negative weights, minimum cost bipartite $\boldsymbol{\mathit{b}}$-matching when $\|\boldsymbol{\mathit{b}}\|_1 = O(m)$, and recovers the running time of the currently fastest algorithm for maximum flow in graphs with unit capacities (Liu-Sidford, 2020). Our algorithm relies on developing an interior point method-based framework which acts on the space of circulations in the underlying graph. From the combinatorial point of view, this framework can be viewed as iteratively improving the cost of a suboptimal solution by pushing flow around circulations. These circulations are derived by computing a regularized version of the standard Newton step, which is partially inspired by previous work on the unit-capacity maximum flow problem (Liu-Sidford, 2019), and subsequently refined based on the very recent progress on this problem (Liu-Sidford, 2020). The resulting step problem can then be computed efficiently using the recent work on $\ell_p$-norm minimizing flows (Kyng-Peng-Sachdeva-Wang, 2019). We obtain our faster algorithm by combining this new step primitive with a customized preconditioning method, which aims to ensure that the graph on which these circulations are computed has sufficiently large conductance.

cs.DS↗

arXiv2018

A Classification-Based Study of Covariate Shift in GAN Distributions

A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the distributions they are trained on. In particular, evaluating the diversity of GAN distributions is challenging and existing methods provide only a partial understanding of this issue. In this paper, we develop quantitative and scalable tools for assessing the diversity of GAN distributions. Specifically, we take a classification-based perspective and view loss of diversity as a form of covariate shift introduced by GANs. We examine two specific forms of such shift: mode collapse and boundary distortion. In contrast to prior work, our methods need only minimal human supervision and can be readily applied to state-of-the-art GANs on large, canonical datasets. Examining popular GANs using our tools indicates that these GANs have significant problems in reproducing the more distributional properties of their training dataset.

cs.LG↗

arXiv2018

Adversarially Robust Generalization Requires More Data

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high confidence. To better understand this phenomenon, we study adversarially robust learning from the viewpoint of generalization. We show that already in a simple natural data model, the sample complexity of robust learning can be significantly larger than that of "standard" learning. This gap is information theoretic and holds irrespective of the training algorithm or the model family. We complement our theoretical results with experiments on popular image classification datasets and show that a similar gap exists here as well. We postulate that the difficulty of training robust classifiers stems, at least partially, from this inherently larger sample complexity.

cs.LG↗

arXiv2018

Round Compression for Parallel Matching Algorithms

For over a decade now we have been witnessing the success of {\em massive parallel computation} (MPC) frameworks, such as MapReduce, Hadoop, Dryad, or Spark. One of the reasons for their success is the fact that these frameworks are able to accurately capture the nature of large-scale computation. In particular, compared to the classic distributed algorithms or PRAM models, these frameworks allow for much more local computation. The fundamental question that arises in this context is though: can we leverage this additional power to obtain even faster parallel algorithms? A prominent example here is the {\em maximum matching} problem---one of the most classic graph problems. It is well known that in the PRAM model one can compute a 2-approximate maximum matching in $O(\log{n})$ rounds. However, the exact complexity of this problem in the MPC framework is still far from understood. Lattanzi et al. showed that if each machine has $n^{1+Ω(1)}$ memory, this problem can also be solved $2$-approximately in a constant number of rounds. These techniques, as well as the approaches developed in the follow up work, seem though to get stuck in a fundamental way at roughly $O(\log{n})$ rounds once we enter the near-linear memory regime. It is thus entirely possible that in this regime, which captures in particular the case of sparse graph computations, the best MPC round complexity matches what one can already get in the PRAM model, without the need to take advantage of the extra local computation power. In this paper, we finally refute that perplexing possibility. That is, we break the above $O(\log n)$ round complexity bound even in the case of {\em slightly sublinear} memory per machine. In fact, our improvement here is {\em almost exponential}: we are able to deliver a $(2+ε)$-approximation to maximum matching, for any fixed constant $ε>0$, in $O((\log \log n)^2)$ rounds.

cs.DS↗

arXiv2017

A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians

Sparsity-based methods are widely used in machine learning, statistics, and signal processing. There is now a rich class of structured sparsity approaches that expand the modeling power of the sparsity paradigm and incorporate constraints such as group sparsity, graph sparsity, or hierarchical sparsity. While these sparsity models offer improved sample complexity and better interpretability, the improvements come at a computational cost: it is often challenging to optimize over the (non-convex) constraint sets that capture various sparsity structures. In this paper, we make progress in this direction in the context of separated sparsity -- a fundamental sparsity notion that captures exclusion constraints in linearly ordered data such as time series. While prior algorithms for computing a projection onto this constraint set required quadratic time, we provide a perturbed Lagrangian relaxation approach that computes provably exact projection in only nearly-linear time. Although the sparsity constraint is non-convex, our perturbed Lagrangian approach is still guaranteed to find a globally optimal solution. In experiments, our new algorithms offer a 10$\times$ speed-up already on moderately-size inputs.

cs.DS↗

arXiv2016

Exploring the Limits of Static Failover Routing

We present and study the Static-Routing-Resiliency problem, motivated by routing on the Internet: Given a graph $G$, a unique destination vertex $d$, and an integer constant $c>0$, does there exist a static and destination-based routing scheme such that the correct delivery of packets from any source $s$ to the destination $d$ is guaranteed so long as (1) no more than $c$ edges fail and (2) there exists a physical path from $s$ to $d$? We embark upon a systematic exploration of this fundamental question in a variety of models (deterministic routing, randomized routing, with packet-duplication, with packet-header-rewriting) and present both positive and negative results that relate the edge-connectivity of a graph, i.e., the minimum number of edges whose deletion partitions $G$, to its resiliency.

cs.NI↗