Paper detects Trojan neural networks with limited or no data.
problem Robustness of DNNs against Trojan attacks in data-scarce scenarios.
method Proposes data-limited and data-free TrojanNet detectors.
result Demonstrates effectiveness of detectors on various datasets.
CLEANN detects and mitigates neural network Trojans without labeled data.
problem Trojans in embedded neural networks that bypass detection during inference.
method Dictionary learning and sparse approximation for identifying Trojan triggers, lightweight algorithm/hardware co-design.
result Efficient real-time execution on resource-constrained platforms, competitive attack resiliency.
Deep learning architectures (DLA) have shown impressive performance in computer vision, natural language processing and so on. Many DLA make use of cloud computing to achieve classification due to the high computation and memory requirements. Privacy and latency concerns resulting from cloud computing has inspired the …
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep reinforcement learning (DRL) agents and can be exploited by an adversary with access to…
Trojans can be inserted into deep neural networks without altering training data.
problem Inserting malicious code into deep learning models without changing training data.
method Patches model parameters in memory to achieve desired behavior on specific inputs.
result Efficient patches can induce trojan behavior with minimal risk of detection.
MISA detects Trojan triggers in neural networks at inference time.
problem Trojan attacks on neural networks that respond to specific trigger patterns.
method MISA uses misattributions to detect anomalous feature activations.
result MISA achieves 96% AUC in detecting Trojan triggers without assumptions.
With the rising popularity of machine learning and the ever increasing demand for computational power, there is a growing need for hardware optimized implementations of neural networks and other machine learning models. As the technology evolves, it is also plausible that machine learning or artificial intelligence wil…
Simple adaptive attacks can jailbreak state-of-the-art safety-aligned language models.
problem Vulnerability of safety-aligned language models to simple adaptive attacks.
method Designing adversarial prompt templates, random search on suffixes, and transfer/prefilling attacks.
result 100% attack success rate on various models including GPT-4, Vicuna, Mistral, and Claude.
Backdoor attacks on DRL-based traffic controllers cause stop-and-go waves or crashes.
problem Vulnerability of DRL-based traffic controllers to machine learning attacks.
method Developed a trigger design methodology based on traffic physics principles.
result Backdoored models can cause stop-and-go traffic waves or AV crashes when triggered.
Deep learning models misclassify malware with added benign features.
problem Detecting malware with deep learning when it's mixed with benign code.
method Trained a deep neural network classifier using benign and malware features. Demonstrated the impact of adding benign features to malware. Used data augmentation to improve classifier robustness.
result Adding benign features to malware significantly increases false negatives.
GTA is the first backdoor attack on GNNs, demonstrating vulnerabilities in graph-oriented security models.
problem Vulnerability of graph neural networks to backdoor attacks.
method Graph-oriented triggers, dynamic adaptation, model-agnostic, attack-extensible.
result Demonstrates severe threats to graph classification and node classification tasks.
While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data from potentially untrustworthy sources, providing adversaries with the opportun…
Timely detection of Hardware Trojans (HTs) has become a major challenge for secure integrated circuits. We present a run-time methodology for HT detection that employs a multi-parameter statistical traffic modeling of the communication channel in a given System-on-Chip (SoC), named as SIMCom. The main idea is to model …
"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.
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.
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.
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.
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.
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.
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…
New method handles uncertainty in adversarial attacks using ensemble noise simulation.
problem Uncertainty in adversarial attacks on neural networks.
method Simulates attacker's noisy perturbation using various gradient-based attack algorithms and a pre-processing Denoising Autoencoder (DAE) defense.
result Significant improvements in post-attack accuracy with the proposed ensemble-trained defense.
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 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.
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.
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…
New black-box attack method improves GNN defense without needing training data.
problem Vulnerability of Graph Neural Networks to adversarial attacks.
method Developed a gradient-based black-box attack algorithm, BBGA, which does not require access to training data.
result BBGA achieves stable attack performance without accessing training sets, and is effective against various defenses.
Robustness of Deep Reinforcement Learning (DRL) algorithms towards adversarial attacks in real world applications such as those deployed in cyber-physical systems (CPS) are of increasing concern. Numerous studies have investigated the mechanisms of attacks on the RL agent's state space. Nonetheless, attacks on the RL a…
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper…
Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations. However, some attacks assume full availability of the victim model, and some require a huge amount of computation, making them less feasible…
This paper improves attacks on recommender systems by solving optimization problems more precisely.
problem Adversarial injection attacks on recommender systems.
method Solving optimization problems for generating fake user interactions more accurately.
result The exact solution for generating fake users leads to a much larger impact on recommender systems.
First robust bandit algorithm for contextual bandits with sub-linear regret.
problem Vulnerability of linear contextual bandit algorithms to adversarial attacks.
method Proposes a robust bandit algorithm for stochastic linear contextual bandits under fully adaptive and omniscient attacks.
result Sub-linear regret under various attacks without requiring attack information.
As machine learning (ML) becomes more and more powerful and easily accessible, attackers increasingly leverage ML to perform automated large-scale inference attacks in various domains. In such an ML-equipped inference attack, an attacker has access to some data (called public data) of an individual, a software, or a sy…
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims to check whether a given instance x was used in the training data or not. A co-me…
Efficient poisoning attack converges to any target classifier with provable convergence.
problem Inducing a corrupted model that misbehaves in favor of an adversary.
method Online convex optimization to find poisoning points incrementally.
result Provably converges to any attainable target classifier.
New adversarial training enhances malware detectors against various attacks.
problem Vulnerability of malware detectors to evasion attacks.
method Proposes a mixture of attacks and adversarial training to improve deep neural networks.
result Significantly enhances robustness of deep neural networks against a wide range of attacks.