Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
problem Adversarial susceptibility of LLMs to generate out-of-domain outputs.
method VALID approach providing adversarial bounds as a certificate.
result Validates LLMs' domain adherence with meaningful certificates.
Two impossibility theorems show formal alignment certification is impossible for AI systems.
problem Formal certification of AI alignment over open-ended domains is impossible.
method Two independent impossibility theorems: Semantic and Statistical barriers.
result No procedure can simultaneously satisfy soundness, completeness, and tractability.
Survey examines challenges of ML in avionic systems certification.
problem Challenges in current certification standards for ML in avionic systems.
method Literature review focusing on robustness and explainability of ML results.
result Current certification standards do not support ML in avionic systems.
Paper improves neural network robustness certification with tighter radii estimates.
problem Certifying neural networks' robustness against adversarial attacks.
method Advanced algorithms for discrete and continuous domains, optimizing sample size, standard deviation, and temperature.
result Significant improvement in certified test-set accuracy with tighter certified radii bounds.
New algorithms learn stability certificates from data, avoiding complex dynamics.
problem Synthesizing stability certificates from complex dynamical systems.
method Developed algorithms to learn certificate functions from trajectory data, establishing generalization error bounds.
result Efficiently learned certificates can be used for adaptive control.
This study improves scalability of randomized smoothing for certifying classifier robustness.
problem Certifying machine learning classifiers against adversarial attacks is challenging and scalable solutions are needed.
method The study reviews and explores randomized smoothing and its derivatives, focusing on scalability.
result The study provides theoretical guarantees and discusses scalability challenges of randomized smoothing.
Improved neural network robustness certification through tighter convex relaxations.
problem Certifying neural network robustness to perturbed and adversarial inputs.
method Exploiting ReLU network structure, novel partition-based certification procedure.
result Tightens existing linear programming relaxations to achieve zero relaxation error asymptotically.
Develops structured noise for more accurate graph classifier robustness certificates.
problem Isotropic noise limits robustness certificates for graph classifiers.
method Randomized smoothing with anisotropic noise distribution.
result Structured-aware robustness certificates provide more accurate predictions.
New method closes certification gap for adversarially trained models.
problem Certifying robustness of adversarially trained neural networks.
method Nonconvex low-rank SDP relaxation with polynomial-time optimization.
result Strong certifications comparable to SDP methods, but with fewer variables.
BagCert efficiently certifies robustness against adversarial patches on image classifiers.
problem Adversarial patches pose a threat to autonomous systems' perception component.
method BagCert combines model architecture and certification procedure for efficient inference.
result BagCert certifies 10,000 examples in 43 seconds on a single GPU, achieving 86% clean and 60% certified accuracy against 5x5 patches.
While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. Defenses based on regularization and adversarial training are often followed by new attacks to defeat them. In this paper, we propose attack-…
Bayesian method synthesizes barrier certificates for unknown systems with latent states.
problem Certifying safety in systems with unknown dynamics and latent states.
method Bayesian inference with Metropolis-Hastings sampler and sum-of-squares program.
result Probabilistic validity of barrier certificates for unknown systems.
CITE algorithm provides anytime-valid certification of model outputs.
problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.
Paper develops tighter risk certificates for contrastive learning models.
problem Statistical theory for contrastive learning is lacking, especially for practical models like SimCLR.
method Develops non-vacuous PAC-Bayesian risk certificates considering practical SimCLR factors.
result Risk certificates for contrastive loss and downstream prediction are much tighter than previous results.
Develops local population-risk certificates for model updates
problem Model updates in machine learning
method Certify population-risk increments around a model
result Certified upper endpoint yields a risk-controlled update rule
The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration. Existing algorithms provide little information about the quality of their current policy before executing it, and thus have limited use in high-stakes applications like healthcare. We address this lack of …
New method provides tighter robustness guarantees for adversarial attacks.
problem Ensuring robustness against adversarial attacks in machine learning models.
method Developed a Second-order Smoothing (SoS) robustness certificate using Gaussian random smoothing.
result SoS certificates are tighter and provide improved robustness on high-dimensional datasets.
TUV Austria proposes certification for ML applications to ensure reliability.
problem Ensuring trust in AI applications to meet societal reliance requirements.
method Holistic approach analyzing security, functionality, data quality, ethics, and criticality levels.
result Certification process for low-risk ML applications in supervised learning.
New protocol identifies impossible edge orientations in causal graphs.
problem Causal-discovery algorithms cannot distinguish edge directions without assumptions.
method Discrete impossibility certificates and oracle queries.
result Upper bound of 1+K expert interactions for DAG recovery. Paper provides efficient robustness certificates for neural networks.
problem Ensuring neural networks are robust against adversarial attacks.
method Two-step approach: 1) Efficient convex optimization for robustness certificates with bounded Hessian eigenvalues, 2) Curvature-based regularization during training.
result Significantly higher certified robust accuracy achieved compared to existing methods.
New attack tricks certifiably robust models into mislabeling images.
problem Defeating certified defenses against adversarial examples.
method Spoofed robustness certificates and large perturbations.
result Certifiably robust models can be fooled by large perturbations.
Conformal Candidate Certification advances offline MBO by certifying candidate designs with statistical guarantees.
problem Offline model-based optimization
method Conformal Candidate Certification (CCC)
result CCC certifies 16.7% of an aggressive proposal pool with 0.990 empirical coverage at nominal 0.90.
New robustness certificates for streaming models with a sliding window.
problem Applying robustness certificates to streaming data with correlated inputs.
method Deriving robustness certificates for models using a sliding window over a sequence of potentially correlated inputs.
result Guarantees hold for the average model performance across the entire stream, independent of stream size.
Geometric technique determines exactness of SDP robustness certificate.
problem Certifying robustness of neural networks to adversarial examples.
method Geometric projection onto hyperbola, SDP relaxation of ReLU activation.
result SDP certificate is exact for a single hidden layer under mild assumptions.
Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning. However, most existing methods only leverage Gaussian smoothing noise and only work for ℓ2 perturbation. We propose a general framework of adversarial certificati…
The paper improves risk certificate tightness for neural networks using PAC-Bayes bounds.
problem Improving the usability of risk certificates for neural networks based on PAC-Bayes bounds.
method Theoretical contributions including KL divergence bounds, efficient methodology for optimization, and methods for optimizing non-differentiable objectives.
result First non-vacuous generalization bounds on CIFAR-10 for neural networks.
Study adversarial perturbations in classification, analyzing learning and certification.
problem Formal study of classification under adversarial perturbations from both learner and third-party perspectives.
method PAC-type semi-supervised learning framework, black-box certification under limited query budget, adversary analysis.
result Existence of a polynomial query complexity adversary implies the existence of a sample efficient robust learner.
Looking for associations among multiple variables is a topical issue in statistics due to the increasing amount of data encountered in biology, medicine and many other domains involving statistical applications. Graphical models have recently gained popularity for this purpose in the statistical literature. Following t…
New method improves robustness of smoothed classifiers against adversarial attacks.
problem Improving robustness of smoothed classifiers against adversarial attacks.
method Proposes worst-case adversarial loss over input distributions as a robustness certificate, and uses duality and smoothness properties to provide an easy-to-compute upper bound.
result Shows superior robustness performance over state-of-the-art certified or heuristic methods.
New framework certifies robustness for regression models.
problem Certifying robustness for regression models is challenging.
method Derives a prediction-centered certificate that exploits local geometry.
result Gradient information yields tighter robustness certificates.
SREC markets are a relatively novel market-based system to incentivize the production of energy from solar means. A regulator imposes a floor on the amount of energy each regulated firm must generate from solar power in a given period and provides them with certificates for each generated MWh. Firms offset these certif…
The paper improves alignment methods for deep neural networks using geometric and spectral analysis.
problem Improving alignment methods for deep neural networks.
method Geometric and spectral analysis of residual Jacobian chains.
result Deterministic and margin-verified results on the transport of dominant singular subspaces across layers.
This paper develops a general theoretical framework to analyze structured sparse recovery problems using the notation of dual certificate. Although certain aspects of the dual certificate idea have already been used in some previous work, due to the lack of a general and coherent theory, the analysis has so far only be…
New approach to adversarial robustness with non-uniform perturbations.
problem Real-world adversaries craft adversarial examples with non-uniform perturbations.
method Proposes non-uniform perturbations based on feature dependencies and data distribution.
result Shows improved robustness to real-world attacks compared to uniform perturbations.
Given a tame knot K presented in the form of a knot diagram, we show that the problem of determining whether K is knotted is in the complexity class NP, assuming the generalized Riemann hypothesis (GRH). In other words, there exists a polynomial-length certificate that can be verified in polynomial time to prove that K…
The paper compares machine learning methods with traditional techniques for pricing and sensitivities of financial products with path-dependent structures.
problem Evaluating financial products with early-termination clauses, especially those with path-dependent structures.
method The paper compares regression methods including randomized recurrent and feed-forward neural networks, and a novel approach using signatures of the underlying price process, with traditional polynomial basis functions for pricing and sensitivities.
result Machine learning algorithms often match the accuracy and efficiency of traditional methods for Asian and look-back options, while randomized neural networks are best for callable certificates.
Paper proposes a dataset quality process for ML systems.
problem Inadequate standards for ML datasets in safety-critical systems.
method Proposes a dataset specification and verification process.
result Demonstrates the process on a railway signal recognition system.
New method certifies deep graph classifiers with tighter risk bounds.
problem Certifying the reliability of deep graph classifiers.
method Linearized deep assignment flows with random initial conditions, using PAC-Bayes risk certification.
result Computes tighter out-of-sample risk certificates efficiently.
Develops certificates for local population-risk increments using cross-fitted ridge calibration.
problem Certifying local population-risk increments in statistical models.
method Cross-fitted ridge calibration for linear feature classes, separating Taylor fluctuations and remainders.
result Certifies measurable updates from the same sample with penalties dependent on empirical geometry.
Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base classifications on randomly noised samples where the noise is additive. In this pap…
Paper reviews robustness in machine learning models and discusses training and certification methods.
problem Ensuring reliability of machine learning models in safety-critical systems.
method Reviews formalisms and discusses training and certification techniques.
result Identifies future research directions in robust machine learning.
Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we introduce a certifiable defense against patch attacks that guarantees for a given image…
ClusTR improves clustering-based models' robustness without adversarial training.
problem Improving clustering-based models' robustness.
method Proposes ClusTR, a clustering-based training framework for robust models without adversarial training.
result ClusTR outperforms adversarially-trained models by up to 4% under strong PGD attacks.
This paper studies the market phenomenon of non-convergence between futures and spot prices in the grains market. We postulate that the positive basis observed at maturity stems from the futures holder's timing options to exercise the shipping certificate delivery item and subsequently liquidate the physical grain. In …
Proposes new convex relaxations for certifying spatial robustness of neural networks.
problem Lack of provable guarantees for robustness against vector field transformations.
method Novel convex relaxations for certifying robustness against vector field transformations.
result First time providing a certificate of robustness against vector field transformations.
The paper provides tighter error bounds for GPR under bounded support noise.
problem Rigorous error quantification for safety-critical applications with bounded noise.
method Using concentration inequalities and low complexity assumptions in RKHS, the paper derives probabilistic and deterministic error bounds for GPR.
result The derived error bounds are substantially tighter than existing state-of-the-art bounds and are particularly well-suited for GPR with neural network kernels.
New method certifies generative models' robustness.
problem Certifying generative models' robustness is challenging due to non-convex sets.
method ApproxLine, a scalable certification method capturing infinite sets or distributions over them.
result ApproxLine provides sound deterministic and probabilistic guarantees.
Improved robustness for deep neural networks with tighter bounds and attacks.
problem Loose upper bounds and prohibitive computation in existing adversarial robustness methods.
method Primal approach with exact Lipschitz certificates for ReLU networks and modern architectures, and novel Wasserstein Distributional Attacks.
result Tighter upper bounds and greater flexibility in attack points compared to existing methods.