Spanning attack improves black-box attacks with unlabeled data.
problem Query inefficiency in black-box attacks due to high input space dimensionality.
method Proposes spanning attack by constraining adversarial perturbations in a low-dimensional subspace via an auxiliary unlabeled dataset.
result Significantly improves query efficiency of black-box attacks.
Study on reward poisoning attacks on CMAB, revealing attackability depends on adversary's knowledge.
problem Reward poisoning attacks on Combinatorial Multi-Armed Bandits (CMAB).
method Provided a sufficient and necessary condition for attackability, devised an attack algorithm.
result Attackability of CMAB depends on adversary's knowledge of the bandit instance.
In this appraisal paper, we evaluate the efficacy of SHIELD, a compression-based defense framework for countering adversarial attacks on image classification models, which was published at KDD 2018. Here, we consider alternative threat models not studied in the original work, where we assume that an adaptive adversary …
Gen-LRA attacks synthetic data leakage without model knowledge.
problem Auditing synthetic data privacy leakage.
method Generative Likelihood Ratio Attack (Gen-LRA).
result Gen-LRA outperforms other attacks across metrics.
Adversarial examples are maliciously perturbed inputs designed to mislead machine learning (ML) models at test-time. They often transfer: the same adversarial example fools more than one model. In this work, we propose novel methods for estimating the previously unknown dimensionality of the space of adversarial inputs…
The paper analyzes security issues in blockchain ecosystems with multiple SSPs and proposes two models for better stake management.
problem Security issues in blockchain ecosystems with multiple SSPs and stake fragmentation.
method Formalized the Multiple SSP Problem and analyzed two architectures: Model M and Model S through convex optimization and game-theoretic lens. result Model S achieves tighter security guarantees through single validator sets and aggregated slashing logic. Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable to topological attacks. To enhance adversarial robustness, we go beyond spectral graph theory to robust graph theory. By challenging the classical graph Laplacian, we propose a new c…
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, onli…
Weighted SVM (or fuzzy SVM) is the most widely used SVM variant owning its effectiveness to the use of instance weights. Proper selection of the instance weights can lead to increased generalization performance. In this work, we extend the span error bound theory to weighted SVM and we introduce effective hyperparamete…
New spanning 3-disks found for unlink in 4-sphere.
problem 2-component unlink in 4-sphere.
method Found infinitely many isotopy classes of Brunnian spanning 3-disks.
result Infinitely many Brunnian spanning 3-disks for 2-unlink in 4-sphere.
Sharp bounds for spanning tree entropy in planar lattices.
problem Estimating spanning tree entropy in planar lattice graphs.
method Using hyperbolic geometry and polyhedra volumes.
result Proved bounds are easy to compute and provide excellent estimates.
Totally geodesic surfaces found in knots and links.
problem Finding totally geodesic surfaces in knots and links.
method Constructing infinite families of knots and links with totally geodesic spanning surfaces in various 3-manifolds.
result Infinite families of knots and links with totally geodesic spanning surfaces in multiple 3-manifolds.
"Feint Attack", as a new type of APT attack, has become the focus of attention. It adopts a multi-stage attacks mode which can be concluded as a combination of virtual attacks and real attacks. Under the cover of virtual attacks, real attacks can achieve the real purpose of the attacker, as a result, it often caused hu…
This paper studies adversarial attacks on Gaussian process bandits.
problem Adversarial attacks on Gaussian process bandits to manipulate optimal function regions.
method Proposes various adversarial attack methods on GP bandits, including white-box and black-box attacks.
result Adversarial attacks can force GP bandits to optima in target regions even with low attack budgets.
The Jones polynomial can be expressed in terms of spanning trees of the graph obtained by checkerboard coloring a knot diagram. We show there exists a complex generated by these spanning trees whose homology is the reduced Khovanov homology. The spanning trees provide a filtration on the reduced Khovanov complex and a …
A new classification method based on Minimum Spanning Trees
problem Improving classification in supervised learning
method Proposing a classification algorithm based on Minimum Spanning Trees
result The proposed method is effective and computationally efficient
Subpopulation attacks poison data to misclassify naturally distributed points.
problem Improving accuracy of machine learning predictions through adversarial data modification.
method Introducing a novel subpopulation attack framework, using influence functions and gradient optimization.
result Subpopulation attacks are effective and stealthy, making them difficult to defend against.
Matryoshka hides secret models in a carrier model, achieving high capacity and robustness.
problem Stealing functionality of private ML data by hiding models in a carrier model.
method Parameter sharing approach exploiting the learning capacity of the carrier model.
result Hides a 26x larger secret model or 8 secret models in the carrier model.
Ancient curves span halfplanes via flow.
problem Ancient solutions to Curve Shortening Flow.
method Constructing infinite family of solutions.
result Spanning halfplane with ancient curves.
Refines knot defect measurement in 3D and 4D.
problem Measuring how far knots are from being alternating.
method Extends spanning surface defect to 4-ball, making comparisons and proving formulas.
result Connected sum formula proven.
Proves bounds on spanning two-forests and random cut sizes.
problem Counting spanning two-forests and estimating random cut sizes.
method Uses pairwise effective resistances and potential theory.
result Establishes bounds on the number of spanning two-forests and average cut size.
Alexander polynomial equals spanning tree count at t=1.
problem Alexander polynomial for spatial graphs.
method Combinatorial constructions generalized to weighted graphs.
result Value of Alexander polynomial at t=1 equals weighted spanning tree count.
Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.
problem Reward-poisoning attacks can manipulate RL agents to learn undesirable policies.
method Categorize attacks by infinity-norm constraint, provide thresholds for feasibility, and develop adaptive attack strategies.
result Adaptive reward-poisoning attacks can achieve the nefarious policy in polynomial steps, while non-adaptive attacks require exponential steps.
We introduce the warping polynomial of an oriented knot diagram. In this paper, we characterize the warping polynomial, and define the span of a knot to be the minimal span of the warping polynomial for all diagrams of the knot. We show that the span of a knot is one if and only if it is non-trivial and alternating, an…
Headless attacks bypass classification heads to fool transfer learning models.
problem Adversarial attacks against transfer learning models without access to the classification head.
method Label-blind adversarial attacks that do not require class-label information.
result Transfer attack lowers ResNet18 accuracy on CIFAR10 by over 40%.
New attack manipulates UCB algorithm, new defense algorithm reduces pseudo-regret.
problem Adversarial attacks on stochastic bandit algorithms.
method Introducing action-manipulation attacks and proposing a robust defense algorithm.
result Proposed defense algorithm reduces pseudo-regret to O(max{log T, A}).
This paper explores evasion attacks against Bayesian models.
problem Bayesian predictive models are vulnerable to evasion attacks.
method Developed gradient-based attacks for specific point predictions and entire posterior distributions.
result Optimal evasion attacks can be designed against Bayesian models.
Adversarial attacks pose a threat to deep neural networks, especially in safety-critical applications.
problem Adversarial attacks can misclassify deep neural networks, leading to safety issues.
method Adversarial attacks are categorized into white-box and black-box attacks based on the attacker's knowledge. They can be targeted or non-targeted.
result Adversarial attacks are effective and can transfer between different models and real-world scenarios.
New approach deflects adversarial attacks by causing them to resemble target classes.
problem Ongoing cycle of stronger defenses being broken by more advanced attacks.
method Combines three detection mechanisms in Capsule Networks to achieve state-of-the-art performance on both standard and defense-aware attacks. Uses human study to show attacks can no longer be called adversarial.
result Attack images can no longer be called adversarial because they are classified the same way as humans do.
New spanning tree model connects knot homology, s-invariant, and exotic discs.
problem Understanding exotic discs in the 4-ball for knots.
method Explicitly defined differential in spanning tree complex, described Rasmussen's s-invariant.
result Identified new infinite family of knots bounding exotic discs.
We derive properties of the cdf of random variables defined as saddle-type points of real valued continuous stochastic processes. This facilitates the derivation of the first-order asymptotic properties of tests for stochastic spanning given some stochastic dominance relation. We define the concept of Markowitz stochas…
New algorithms find optimal policies without knowing MDP span.
problem Finding optimal policies in MDPs without knowing span.
method Horizon calibration and span penalization techniques.
result First algorithms achieving optimal span-based complexity without prior knowledge.
RayS attack improves hard-label adversarial attacks by reducing query complexity and identifying false robust models.
problem Challenges in hard-label adversarial attacks, especially in terms of effectiveness and efficiency.
method Reformulates continuous problem into discrete problem without gradient estimation and uses a fast check step to eliminate unnecessary searches.
result Significantly reduces the number of queries needed for hard-label attacks and identifies false robust models.
Non-spanning identification of scheduled event risk in option pricing.
problem Separating continuous surface from scheduled jump in option pricing.
method Modeling FOMC decisions, CPI releases, and NFP reports as deterministic-time jumps in risk-neutral option pricing.
result Improves held-out event-spanning pricing with Gaussian and two-component mixture jumps.
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent (PGD) can achieve relatively high attack success rates within moderate iterates. How…
Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques …
New invariants measure how far spanning surfaces are from being compressible.
problem Understanding how essential spanning surfaces are in 3-manifolds.
method Introducing algebraic and geometric essence invariants, proving plumbing respects algebraic essence, and extending results to arbitrary 3-manifolds.
result Plumbing respects the algebraic essence of spanning surfaces, extending Ozawa's theorem.
New attacks reveal membership in label-only ML models.
problem Vulnerability of ML models to membership inference attacks.
method Developed decision-based membership inference attacks.
result Label-only exposures are vulnerable to membership leakage.
Adversarial attacks for image classification are small perturbations to images that are designed to cause misclassification by a model. Adversarial attacks formally correspond to an optimization problem: find a minimum norm image perturbation, constrained to cause misclassification. A number of effective attacks have b…
This paper proposes multi-view attack strategies for deep models.
problem Vulnerability of multi-view deep models to adversarial attacks.
method Two multi-view attack strategies: two-stage attack (TSA) and end-to-end attack (ETEA).
result Proposed multi-view attack strategies are effective on multi-view deep models.
New attacks can infer model training membership using only label predictions, not confidence.
problem Inferring whether a data point was used to train a machine learning model.
method Evaluate model's predicted labels under perturbations to infer membership.
result Label-only attacks perform as well as confidence-based attacks and break defenses that rely on confidence masking.
Pixle attacks images by rearranging pixels, bypassing neural networks.
problem Vulnerability of neural networks to black-box adversarial attacks.
method A novel attack that rearranges a small number of pixels in images.
result Successfully attacks a high percentage of samples on various datasets and models.
Efficiently attacks large-scale graphs without using the whole graph.
problem Vulnerability of graph neural networks to adversarial attacks.
method Simplified Gradient-based Attack (SGA) method for large-scale graphs.
result SGA achieves significant time and memory efficiency improvements.
Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease detection or unmann…
We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of…
A new method uses adversarial attacks to detect other adversarial attacks.
problem Detecting iterative adversarial attacks on deep neural networks.
method Using the Carlini-Wagner (CW) attack as a detector itself, under certain assumptions.
result The method provides asymptotically optimal separation of original and attacked images.
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because most methods used to generate such perturbations rely either on detailed model inf…
Study Murasugi sum in 4D for knotted surfaces, defining arborescent surfaces.
problem Defining and understanding Murasugi sum in 4D for knotted surfaces.
method Introduced a 4D Murasugi sum to define arborescent knotted surfaces.
result Defined and studied arborescent knotted surfaces using 4D Murasugi sum.