New method for cost-sensitive robustness against adversarial examples.
problem Real-world applications where some adversarial transformations are more harmful than others.
method Integrates a cost matrix into the robust training method to optimize for cost-sensitive robustness.
result Models with reduced cost-sensitive robust error and maintained classification accuracy.
New algorithms for planning with adversarial changes in costs.
problem Planning with adversarial changes in costs over time.
method Developed algorithms for adversarial SSP with high probability regret bounds.
result Obtained sub-linear regret bounds for adversarial SSP.
This paper proposes CSADA to make DNNs cost-sensitive.
problem Over-parameterization challenges cost-sensitive classification in DNNs.
method CSADA framework using adversarial data augmentation.
result CSADA effectively minimizes overall cost and reduces critical errors.
Study adversarial attacks on cost-sensitive classifiers.
problem Safety-critical classification problems with cost-sensitive predictions.
method Used state-of-the-art adversarially-resistant neural networks and analyzed as a two-player zero-sum game.
result Introduced a new cost-sensitive attack that performs better than targeted attacks in some cases.
New framework for robustness guarantees in discrete domains.
problem Adversarial robustness in constrained discrete domains.
method Graphical framework for adversarial costs, accommodating complex cost functions.
result Provably minimal adversarial cost and robustness guarantees.
This paper tackles near-optimal adversarial RL with switching costs, providing algorithms and matching lower bounds.
problem Adversarial RL with switching costs, where loss distribution can be non-stationary or adversarial.
method Developed novel switching-reduced algorithms with matching lower bounds for known and unknown transition functions.
result Achieved near-optimal performance in adversarial RL with switching costs, matching theoretical lower bounds.
Free adversarial training improves robustness without generating adversarial examples.
problem Training robust models against adversarial attacks is costly and impractical for large-scale datasets.
method Recycles gradient information from parameter updates to generate adversarial examples.
result Free adversarial training achieves comparable robustness to PGD training at negligible cost.
We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We measure the player's performance using a new notion of regret, also known as policy regret, which better captures the adversary's adaptiveness…
Algorithm for bandits with switching costs achieves optimal regret bounds.
problem Optimal regret bounds for stochastic and adversarial bandits with switching costs.
method Adaptation of Tsallis-INF algorithm with no prior knowledge of regime or time horizon.
result Achieves minimax optimal regret bounds in various settings.
New interpretation of OT regularization as adversarial ground cost.
problem Optimal transport (OT) regularization for machine learning.
method Using Fenchel duality, interpret convex OT regularization as adversarial ground cost.
result Access to a robust dissimilarity measure on the ground space.
Proposes WPGD for cost-sensitive adversarial training in deep learning.
problem Balancing robustness and accuracy in adversarial training.
method WPGD solves an optimal transport problem on the output space of the network.
result WPGD provides finer control over robustness-accuracy trade-off.
Study cyber-attacks on RL algorithms, focusing on cost signal manipulation.
problem Adversarial manipulation of cost signals in reinforcement learning.
method Quantitative analysis of TD( λ λ λ ) and Q Q Q -learning algorithms under manipulation. result Bound on approximation error for TD( λ λ λ ) and convergence properties for Q Q Q -learning under stealthy attacks. New algorithm reduces regret in Bandits with Knapsack problem.
problem Online learning with budget constraints and adversarial rewards.
method Proposes EXP3.BwK and EXP3++.BwK algorithms achieving optimal regret.
result Achieves optimal regret in adversarial setting and almost optimal in stochastic setting.
Generative models use EOT cost for better image generation.
problem Developing models to learn implicit distributions for image generation.
method Two models: one-shot optimization with EOT cost and adversarial game with EOT cost.
result Improved image generation performance on MNSIT.
Study examines trading costs on Uniswap, finding adversarial slippage is significant for large trades and certain assets.
problem Analyzing costs and slippage in decentralized exchanges (DEXs).
method Empirical evaluation of Uniswap's USDC-ETH and PEPE-ETH pools, calculating slippage and reordering slippage.
result Adversarial slippage is significant for large trades and certain assets like PEPE.
Study statistical guarantees for DRO with OT and OT-regularized divergences.
problem Enhancing adversarial robustness in machine learning models.
method Derive concentration inequalities for supervised learning via DRO-based adversarial training.
result First to cover soft-constraint costs and reweighting mechanisms in adversarial training.
New method minimizes regret in AMDP with high probability.
problem Pessimistic regret analysis in AMDP.
method Developed a new policy search method achieving optimistic regret.
result Achieved sublinear optimistic regret with high probability.
Adversarial training adds dynamic perturbations to neural networks for robustness.
problem Accuracy trade-off and lack of diversity in adversarial examples.
method Dynamic adversarial perturbations in the parameter space of neural networks, updating perturbation biases during training.
result Adversarial training with negligible cost and reduced accuracy trade-off.
New algorithm controls linear systems with bandit feedback, achieving optimal regret.
problem Controlling linear systems with bandit feedback under adversarial costs.
method Developed a new algorithm for linear control with memory optimization technique.
result Achieved optimal regret growth proportional to square root of time horizon.
New algorithm achieves logarithmic regret for adversarial online control.
problem Online linear-quadratic control in systems with adversarial disturbances.
method Characterization of optimal offline control law, reduced to online learning with approximate advantage functions.
result First algorithm with logarithmic regret for arbitrary adversarial disturbance sequences.
New method certifies joint adversarial robustness of model ensembles.
problem Ensuring robustness of model ensembles against adversarial attacks.
method Proposes a novel technique to certify joint robustness, building on prior work on single-model robustness certification.
result Demonstrates the effectiveness of certifying joint robustness of ensembles, improving understanding of ensemble defenses.
New framework improves adversarial robustness in one-stage L2D.
problem Adversarial robustness in one-stage Learning-to-Defer (L2D).
method Formalizes attacks, proposes cost-sensitive adversarial surrogate losses, establishes theoretical guarantees.
result Improves robustness against untargeted and targeted attacks while preserving clean performance.
New method enhances adversarial robustness of deep learning models.
problem Improving the robustness of deep learning models against adversarial attacks.
method Optimal transport regularized divergences applied to distributionally robust optimization.
result Improved adversarial robustness on CIFAR-10 and CIFAR-100 datasets.
In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art models are vulnerable to adversarial examples: legitimate examples added by small perturbations which are unnoticeable to human eyes. Adversari…
A new algorithm finds minimizers in dueling optimization with a monotone adversary.
problem Finding minimizers in dueling optimization with a monotone adversary.
method Introduces and studies dueling optimization with a monotone adversary, designs an efficient randomized algorithm.
result Efficient algorithm incurs cost O ( d ) O(d) O ( d ) and iteration complexity O ( d log ( 1 / ε ) 2 ) O(d\log(1/\varepsilon)^2) O ( d log ( 1/ ε ) 2 ) , asymptotically optimal. Optimal control theory applied to machine learning adversarial attacks.
problem Adversarial machine learning threats and detection challenges.
method Optimal control theory applied to machine learning systems.
result Advances in control theory and reinforcement learning can enhance adversarial machine learning research.
The paper uses optimal transport to find the minimum loss in adversarial classification.
problem Understanding the robustness of machine learning classifiers to adversarial attacks.
method Optimal transport to characterize minimum possible loss in adversarial classification scenarios.
result The minimum transportation cost between class distributions provides a lower bound on classification performance.
In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…
DL models for MTS regression are vulnerable to adversarial attacks, posing risks in safety-critical applications.
problem Vulnerability of DL models to adversarial examples in MTS regression.
method Adversarial attack generation techniques from image classification were adapted for MTS.
result All state-of-the-art DL regression models (CNN, LSTM, GRU) are vulnerable to adversarial attacks.
New method reduces regret for sparse adversarial SSP problems.
problem Sparse adversarial Stochastic Shortest Path problem.
method Proposed ℓ r \ell_r ℓ r -norm regularizers for adaptive sparsity. result Regret scales with log M \sqrt{\log M} log M instead of log S A \sqrt{\log SA} log S A . Game theory helps machine learn better from adversarial queries.
problem Adversarial evasion in machine learning prediction.
method Repeated Bayesian Sequential Game to balance classifier selection and query type.
result Learner selects appropriate classifier for clean vs. adversarial queries.
Subgradient algorithm achieves optimal regret for both adversarial and i.i.d. costs on the simplex.
problem Achieving optimal regret for both adversarial and i.i.d. costs on the simplex.
method Demonstrates the universality of the Subgradient algorithm for online learning on the simplex.
result Shows simultaneous O ( N ) O(\sqrt N) O ( N ) regret for adversarial costs and O ( 1 ) O(1) O ( 1 ) pseudo-regret for i.i.d. costs. TRASHFIRE improves model robustness by analyzing training rates and costs.
problem Understanding and predicting model robustness under adversarial conditions.
method Survival models, worst-case examples, cost-aware analysis.
result Deeper models offer marginal robustness gains due to inference time, not inherent robustness.
BPN defends against adversarial attacks by generating beneficial perturbations.
problem Adversarial attacks cause deep neural networks to misclassify clean inputs.
method BPN generates beneficial perturbations during training to neutralize future adversarial attacks.
result BPN is robust to adversarial examples and more efficient than classical adversarial training.
Study optimal transport for robust optimization, showing how adversary's strategy relates to regularization.
problem Optimizing under uncertain parameters with a fictitious adversary reshaping a reference distribution.
method Introduces optimal transport and regularization to relate robustification to variation and Lipschitz norms.
result Conditions for existence and computability of Nash equilibrium between decision-maker and adversary.
AdvMind detects adversary intent in black-box attacks with high accuracy.
problem Detecting adversary intent in black-box adversarial attacks is challenging.
method AdvMind accounts for adversary adaptiveness and synthesizes queries to expose intent.
result AdvMind detects adversary intent with over 75% accuracy after observing less than 3 query batches.
New algorithms tackle adversarial combinatorial bandits with switching costs.
problem Adversarial combinatorial bandits with switching costs.
method Design algorithms operating in batches to restrict switches, proving lower bounds and achieving upper bounds on regret.
result Achieved upper bounds on regret for both bandit and semi-bandit feedback settings.
YOPO reduces adversarial training time by one forward/backward pass per group of updates.
problem Adversarial training's high computational cost limits deep learning's robustness.
method YOPO uses the Pontryagin's Maximal Principle to limit propagation to the first layer.
result YOPO achieves comparable defense accuracy with significantly less computational time.
Optimizes query routing to LLMs under cost and resource constraints.
problem Non-uniform or adversarial batching in per-query routing methods leads to cost inefficiency.
method Batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch.
result Robust routing framework improves accuracy by 1-14% over non-robust methods.
Paper analyzes adversarial risk using optimal transport.
problem Poor performance of machine learning on adversarial data.
method Optimal transport perspective, optimal transport plans (couplings), convexity, smoothness assumptions.
result Fundamental limits on adversarial risk calculated for various datasets.
Paper proposes an adversarial sampling method for efficient extreme classification.
problem Training classifiers over many classes is computationally expensive.
method Adversarial sampling to draw negative samples from an adversarial model.
result Significantly reduces training time by an order of magnitude.
Generalised regularisation equals robustness for exotic function classes.
problem Adversarial examples highlight the need for robust models in exotic function classes.
method Equality result linking distributional robustness and Lipschitz regularisation.
result Certified robustness of Lipschitz-regularised models with mild assumptions.
New method shows adversarial training can be as effective as traditional training without the high cost.
problem The high cost of adversarial training limits its practical application.
method Using FGSM with random initialization and efficient training techniques.
result Adversarial training with FGSM can achieve robust accuracy comparable to PGD-based training at a lower cost.
RL agents learn to detect and mitigate adversarial attacks.
problem Adversarial attacks on Deep RL algorithms deployed in real-life applications.
method Meta-Learned Advantage Hierarchy (MLAH) agent using meta-learning for online robustness.
result The MLAH agent exhibits hierarchical coping behaviors and maintains higher reward distributions over time.
The paper identifies potential adversarial samples near decision boundaries of neural networks.
problem Vulnerability of deep neural networks to small perturbations of inputs.
method Developed a method to explore near decision boundaries of trained classifiers to identify potential adversarial samples.
result Potential adversarial samples represent only 61% of the test data but cover more than 82% of adversarial samples produced by iFGSM and 92% of those by DeepFool on CIFAR10.
Study adversarial attacks on automated trading systems.
problem Robustness of deep learning models in algorithmic trading.
method New attacks with size constraints to evaluate model robustness.
result Realistic adversarial attacks can fool automated trading systems.
Efficient algorithm controls unknown systems with adversarial perturbations.
problem Controlling unknown linear systems with adversarial perturbations and convex losses.
method Measures regret against an optimal linear policy, provides efficient algorithm with sublinear regret bound.
result First efficient algorithm with sublinear regret bound of T^{2/3}.
Adversarial training improves audio classifier robustness.
problem Improving robustness of audio classifiers against adversarial attacks.
method Adversarial training of deep neural networks on audio data.
result Adversarially trained models can resist higher perturbations and fooling rates.