MixTrain improves verifiable robustness of neural networks without sacrificing efficiency.
problem Efficiently making neural networks robust against adversarial attacks.
method Stochastic robust approximation and dynamic mixed training techniques.
result Achieves up to 95.2% verified robust accuracy with significantly reduced training time.
VeriGB verifies robustness of gradient boosted models.
problem Proving robustness of gradient boosted models.
method VeriGB encodes model and robustness as SMT formula for verification.
result VeriGB proves robustness of large gradient boosted models.
IBP-R improves verified adversarial robustness with simple, effective interval bound propagation.
problem Improving verifiability of adversarially trained networks.
method Coupling adversarial attacks with interval bound propagation for minimized verification gap.
result State-of-the-art verified robustness-accuracy trade-offs for small perturbations on CIFAR-10.
Method verifies robustness of graph neural networks to graph perturbations.
problem Vulnerability of graph neural networks to adversarial attacks.
method Proposes efficient method for certifying robustness to graph perturbations.
result Efficient computation of robustness certificates for graph neural networks.
New method CROWN-IBP combines IBP and CROWN for efficient verifiable robust neural networks.
problem Training verifiably robust neural networks is challenging and computationally expensive.
method CROWN-IBP combines interval bound propagation and linear relaxation for efficient training.
result CROWN-IBP achieves significant improvements in verifiable robustness on MNIST and CIFAR datasets.
New approach verifies tree ensembles efficiently, making them more robust.
problem Verifying robustness of decision tree ensembles against evasion attacks is NP-hard.
method Identified large-spread ensembles, proposed verifiable learning, designed training algorithm.
result Large-spread ensembles can be verified in polynomial time and are more robust.
This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i.e., networks that provably satisfy some desired input-output properties. The key idea is to simultaneously train two networks: a predictor network that performs the task at hand,e.g., predicting…
Researchers find floating point errors can mislead neural network verifiers.
problem Floating point arithmetic inaccuracies mislead neural network verifiers.
method Efficiently searches inputs and constructs neural network architectures to exploit verification errors.
result Floating point errors can systematically mislead neural network verifiers.
New method verifies neural network robustness globally using generative models.
problem Verifying robustness of neural networks using generative models.
method Proposes a global robustness notion based on generative models.
result Demonstrates the effectiveness of the proposed method in verifying neural networks.
Unified convex relaxation framework for neural network robustness verification.
problem Inability to achieve tight verification of neural networks against adversarial attacks.
method Unified convex relaxation framework for neural networks of various architectures and nonlinearities.
result Exact solution to convex-relaxed problem does not significantly improve verification gap.
This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.
problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. IBP simplifies robust training for large networks.
problem Training robust neural networks with scalable methods.
method Interval Bound Propagation (IBP) for robust training.
result IBP enables training large provably robust networks.
Semantify-NN verifies neural network robustness against semantic perturbations.
problem Verifying robustness of neural networks against semantic adversarial attacks.
method Inserting semantic perturbation layers (SP-layers) into neural networks to verify robustness.
result Semantify-NN significantly improves robustness verification performance over ℓp-norm-based methods. The paper analyzes different neural network architectures for 3D point cloud processing.
problem Understanding the effects of specific intermediate-layer network architectures on 3D point cloud processing.
method Designing five metrics to diagnose various types of DNNs and conducting comparative studies.
result The hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs are verified.
GPUPoly verifies large neural networks robustly on GPUs.
problem Proving robustness of deep neural networks is crucial but challenging.
method Custom polyhedra algorithms on GPUs.
result GPUPoly can verify 1M neuron networks in 34.5 ms.
New probabilistic approach to neural network robustness.
problem Challenges in verifying neural network robustness.
method Probabilistic robustness approach, abstract interpretation, importance sampling.
result Practical algorithm for checking probabilistic robustness of neural networks.
This work improves neural network robustness to symbol substitutions using formal verification.
problem Neural networks' vulnerability to adversarial attacks, especially under discrete text perturbations.
method Formal verification using Interval Bound Propagation on a simplex model of input perturbations.
result Models show improved verified accuracy under perturbations with formal guarantees.
Automatically verifies robustness of SVMs against adversarial examples.
problem Ensuring SVMs are robust to adversarial attacks.
method Abstract verification using interval domain and reduced affine forms.
result Encouragingly high percentages of provable robustness on MNIST test set.
New method preserves both benign and robust accuracy in deep neural networks.
problem Large neural networks have high computational and storage costs.
method Pruning with fine-tuning to preserve both benign and robust accuracy.
result Average 93% benign accuracy, 92.5% empirical robust accuracy, and 85.0% verifiable robust accuracy preserved while compressing by 10x.
New expressive losses improve adversarial robustness without sacrificing accuracy.
problem Training networks for robustness at the expense of accuracy.
method Formalizing expressivity, using convex combinations of adversarial attacks and IBP bounds.
result Trivial expressive losses yield state-of-the-art results in various settings.
We verify CNNs using reachability analysis and transformations.
problem Verifying neural-based perception systems implemented by CNNs.
method Reachability analysis for feed-forward neural networks with MILP encodings.
result The notion of local robustness cannot be captured by previous robustness notions.
Efficiently trains robust models with faster and more stable interval bounds.
problem Training verifiably robust models against adversarial attacks.
method Integrates interval arithmetic and an additional cost function term to keep hidden layer bounds small.
result Comparable or better results achieved with fewer training iterations and more stability.
This work verifies recurrent neural networks using DFA and shows some are robust to adversarial samples.
problem Verifying recurrent neural networks for adversarial robustness.
method Metric for string distance, DFA for oracle, Tomita grammars for testing.
result Some recurrent networks are robust to adversarial samples.
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.
Introduces RMEE for robust classification, improving MEE's performance in noisy conditions.
problem Improving robustness of MEE criterion for noisy classification.
method Analyzed optimal error distribution, introduced RMEE with half-quadratic optimization.
result RMEE achieves better robustness in noisy conditions compared to original MEE.
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.
New method certifies global robustness of neural networks efficiently.
problem Adversarial examples threaten certifiably robust neural networks.
method Formalized global robustness, adapted widely-used architectures with efficient global Lipschitz bounds.
result Certifiable robust models achieve state-of-the-art verifiable accuracy with negligible costs.
Study analyzes and enhances robustness of neural networks for classification and regression.
problem Understanding and improving robustness of neural network predictions.
method Computes reachable sets of neural networks using over- and under-approximations.
result Approach outperforms adversarial attacks and state-of-the-art classifier verification methods.
The paper verifies the robustness of classifier ensembles against randomized attacks.
problem Ensuring classifier ensembles are robust against arbitrary randomized attacks.
method Formal verification procedure using SMT and MILP encodings to assess robustness.
result Proves the NP-hardness of the robustness-checking problem and provides upper bounds on attack sets.
FROWN optimizes neural network robustness, improving safety in deep learning.
problem Ensuring robustness of neural networks against adversarial attacks.
method Optimization-based approach to tighten robustness certificates.
result Deterministic CROWN solutions are optimal under mild constraints.
Study robustness of split conformal prediction in data contamination setting.
problem Robustness of split conformal prediction under data contamination.
method Analyze split conformal prediction's performance in a contaminated data setting and propose a new method.
result Demonstrated the impact of corrupted data on prediction intervals' coverage and efficiency.
A new framework for verifying robustness of neural networks.
problem Verifying the robustness of neural networks against adversarial attacks.
method LayerCert framework exploiting the nested hyperplane arrangement structure of ReLU networks.
result LayerCert reduces the number and size of convex programs needed for robustness verification.
Study shows how bias in optimization affects robustness in adversarial settings.
problem Understanding and mitigating implicit bias in adversarially robust models.
method Analyzes the implicit bias in robust empirical risk minimization and its impact on generalization.
result Implicit bias in optimization can significantly affect robust generalization.
We study the robustness of classifiers to various kinds of random noise models. In particular, we consider noise drawn uniformly from the ℓ_p ball for p∈[1,∞] and Gaussian noise with an arbitrary covariance matrix. We characterize this robustness to random noise in terms of the distance to the decisio…
Paper explores robustness of CCS model for matrix completion.
problem Robustness of cross-concentrated sampling model against sparse outliers.
method Proposes Robust CUR Completion (RCURC) algorithm for efficient non-convex iterative matrix completion.
result Empirical validation of RCURC's efficiency and robustness in synthetic and real datasets.
Unified approach to verify NN properties using ReLU's unique polytope structure.
problem Lack of robustness and interpretability in ReLU NNs for risk-sensitive applications.
method Identifying and traversing the local polytopes of ReLU NNs, developing an algorithm to verify properties.
result Unified approach to examine network behavior in risk-sensitive settings.
Framework verifies global correctness of neural networks for perception tasks.
problem Verifying robustness of neural networks is insufficient; global correctness needs to be ensured.
method Specified a state space and observation process to define the target input space. Tiled the spaces and compared ground truth and network output bounds to deliver error bounds.
result Framework can verify error bounds globally over the target input space and detect illegal inputs.
Validates neural networks inputs to protect against adversarial examples.
problem Ensuring neural networks robustness against adversarial attacks.
method Runtime local robustness verification based on normal distribution of robustness radii.
result Improves neural network accuracy and protects against adversarial examples.
We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the ℓ2 norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…
New mechanisms from primate vision improve neural network robustness.
problem Demonstrating robust neural networks to small adversarial perturbations.
method Investigated two biologically plausible mechanisms: non-uniform retina sampling and receptive field diversity.
result Non-uniform retina sampling and receptive field diversity improve adversarial robustness.
ViTaX provides formal guarantees for targeted explanations in safety-critical systems.
problem Need trustworthy explanations for safety-critical deep neural networks.
method Formal reachability analysis for targeted, semifactual explanations.
result First method to provide formally guaranteed explanations of model resilience.
Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural Networks, using the well-developed means of Boolean satisfiability. Our…
Exact generalization guarantees for robust models using Wasserstein distance are established.
problem Capturing data uncertainty and distribution shifts in machine learning models.
method Establishes exact generalization guarantees for robust models based on the Wasserstein distance, covering various cases and transport costs.
result Exact generalization guarantees are provided for a wide range of cases, including deep learning objectives with nonsmooth activations.
Paper solves robust multi-dimensional scaling with accelerated projections.
problem Localize point locations from noisy pairwise distances.
method Alternating projections with tangent space acceleration.
result Linear convergence of reconstructed points to original points.
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.
Framework combines adversarial training and provable robustness for neural networks.
problem Training certifiably robust neural networks with provable robustness guarantees.
method Formulates joint optimization problem with adversarial and provable robustness objectives; develops gradient-descent technique.
result Consistently matches or outperforms prior approaches for provable l infinity robustness on MNIST and CIFAR-10.
Paper proposes dense average network for improved power load forecasting.
problem Improving power load forecasting accuracy to save millions for the power industry.
method Introduces dense average connection and constructs dense average network for power load forecasting.
result Proposed model outperforms existing methods on public datasets.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.