Related papers: Symmetry Defeats Auditing
This paper is concerned with learning the input-output mapping of general nonlinear dynamical systems. While the existing literature focuses on Gaussian inputs and benign disturbances, we significantly broaden the scope of admissible…
In adaptive data analysis, a mechanism gets $n$ i.i.d. samples from an unknown distribution $D$, and is required to provide accurate estimations to a sequence of adaptively chosen statistical queries with respect to $D$. Hardt and Ullman…
Many recent self-supervised frameworks for visual representation learning are based on certain forms of Siamese networks. Such networks are conceptually symmetric with two parallel encoders, but often practically asymmetric as numerous…
Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…
In this paper, we engage with and expand on the keynote talk about the Right to Audit given by Prof. Christian Sandvig at the IC2S2 2021 through a critical reflection on power asymmetries in the algorithm auditing field. We elaborate on the…
Object recognition in humans depends primarily on shape cues. We have developed a new approach to measuring the shape recognition performance of a vision system based on nearest neighbor view matching within the system's embedding space.…
We study conformal inference in non-exchangeable environments through the lens of Blackwell's theory of approachability. We first recast adaptive conformal inference (ACI, Gibbs and Cand\`es, 2021) as a repeated two-player vector-valued…
We revisit the problem of estimating the center of symmetry $\theta$ of an unknown symmetric density $f$. Although stone (1975), Eden (1970), and Sacks (1975) constructed adaptive estimators of $\theta$ in this model, their estimators…
Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not…
Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of…
We study whether state-of-the-art AI coding agents, given the same data and research question, produce the same empirical results. Deploying 150 autonomous Claude Code agents to independently test six hypotheses about market quality trends…
Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior…
The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle…
We propose an inverse-design approach for computational spectrometers in which the scattering media are topology-optimized to achieve better performance in inference of unknown spectra. Unlike traditional end-to-end approaches, our inverse…
We explore the R\'enyi entanglement entropies of a one-dimensional (line) subsystem of length $L$ embedded in two-dimensional $L\times L$ square lattice for quantum spin models whose ground-state breaks a continuous symmetry in the…
Generalization, the ability to perform well beyond the training context, is a hallmark of biological and artificial intelligence, yet anticipating unseen failures remains a central challenge. Conventional approaches often take a…
Modern experimental methods enable the creation of self-assembly building blocks with tunable interactions, but optimally exploiting this tunability for the self-assembly of desired structures remains an important challenge. Many studies of…
In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the…
Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…
The purpose of this note is to highlight and address inaccuracies in the convergence guarantees of SCvx, a nonconvex trajectory optimization algorithm proposed by Mao et al. (arXiv:1804.06539), and make connections to relevant prior work.…