FATE framework attacks graph learning models to amplify bias deceptively.
problem Achieving poisoning attacks on graph learning models to exacerbate bias deceptively.
method Bi-level optimization problem and meta learning-based framework named FATE.
result FATE amplifies bias of graph neural networks while maintaining downstream task utility.
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
problem Protecting DNN models from adversarial and out-of-distribution inputs.
method Diverse input denoising verifiers and disagreement-diversity ensemble learning.
result XEnsemble achieves high defense and detection success rates.
Unified pipeline detects multi-turn deception using geometric signals.
problem Detecting multi-turn deceptive interactions in LLMs.
method Geometric signaturization via genetic prompt optimization.
result Compact geometric model achieves high recall and F1 scores.
This paper introduces a new method to deceive causal structure learning by omitting data.
problem Deceiving causal structure learning algorithms with incompletely observed data.
method Adversarial missingness attack to bias the learned causal structures.
result Theoretical and practical attack mechanisms are developed for various SCMs.
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
problem Adversarial attacks on ML-aided visualizations.
method Identifying attack surface and exemplifying five adversarial attacks.
result Adversaries can induce various attacks, like creating arbitrary and deceptive visualizations.
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attr…
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary by omitting probability scores, significantly impacting the utility of the provid…
This paper optimizes cybersecurity resource allocation in networks with heterogeneous attacker and defender valuations.
problem Optimizing cybersecurity resource allocation in networks with heterogeneous attacker and defender valuations.
method Combining strategic behavior of players with contagion dynamics, a method is extended to determine optimal resource allocation based on simple network metrics weighted by risk profiles.
result The asymmetry between attacker and defender valuations drives optimal attack and defense strategies, shaping system resilience.
Study investigates how AI can create and detect deceptive explanations, finding they can fool humans but ML can detect them.
problem The risk of deceptive AI explanations increasing trust issues and economic risks.
method Investigates creation and detection of deceptive explanations using AI models and machine learning methods.
result Deceptive explanations can fool humans, but ML can detect them with high accuracy.
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic robustness property is still lack of thorough investigation. This work aims to qualitat…
New method lures adversaries to choose false directions in black-box attacks.
problem Improving robustness against black-box transfer attacks.
method Incorporates a removable neural network to induce a luring effect.
result Demonstrates effectiveness in thwarting state-of-the-art attacks.
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-of-the-art machine learning techniques, such as deep neural networks, can provi…
Paper exposes vulnerabilities in interpreting machine learning models using adversarial attacks on PD plots.
problem Vulnerability of permutation-based interpretation methods, particularly PD plots, to adversarial attacks.
method Adversarial framework to manipulate black-box models and produce deceptive PD plots.
result It is possible to hide discriminatory behaviors in machine learning models through interpretation tools like PD plots.
The study detects deceptive language in business communication using AI.
problem Deceptive language in business communication.
method Combining classical rhetoric, communication psychology, and linguistic theory with computational textual analysis and transformer models.
result Detection accuracies of over 99% achieved in controlled settings.
Framework trains safe agents avoiding deceptive behavior.
problem Training safe agents from unsafe incentives.
method Formal settings, causal influence analysis, maximizing non-mediated effects.
result Agents avoid manipulating delicate state for rewards.
Systematic review of ML models for detecting social media deception.
problem Detecting fake news, spam, and fake accounts on social media.
method 36 studies evaluated using PROBAST tool, identifying biases and limitations.
result Over-reliance on accuracy in imbalanced data settings is a flaw.
Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been proposed to detect phishing websites. These techniques are dependent on the features …
Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm on four deceptive games, which are specially designed to provide challenges to …
RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.
problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.
In online discussion communities, users can interact and share information and opinions on a wide variety of topics. However, some users may create multiple identities, or sockpuppets, and engage in undesired behavior by deceiving others or manipulating discussions. In this work, we study sockpuppetry across nine discu…
Phishing is the simplest form of cybercrime with the objective of baiting people into giving away delicate information such as individually recognizable data, banking and credit card details, or even credentials and passwords. This type of simple yet most effective cyber-attack is usually launched through emails, phone…
Historically, machine learning in computer security has prioritized defense: think intrusion detection systems, malware classification, and botnet traffic identification. Offense can benefit from data just as well. Social networks, with their access to extensive personal data, bot-friendly APIs, colloquial syntax, and …
Deep learning uses alphabet frequencies to accurately classify fake news.
problem Classifying fake news from trustworthy news.
method Used deep learning algorithms on alphabet frequencies of text without sequence information.
result Achieved high accuracy (85%) in classifying fake news.
This work challenges the assumption that shorter conformal prediction intervals are always better.
problem The conventional evaluation of conformal prediction metrics (coverage and interval length) may not fully capture the quality of predictions.
method The Prejudicial Trick (PT) is introduced, which probabilistically returns either a null interval or a longer one to maintain valid coverage while potentially reducing interval length.
result The Prejudicial Trick can yield deceptively shorter intervals without compromising coverage, but introduces practical vulnerabilities.
This paper tackles sandbagging in AI safety evaluations.
problem AI agents may hide dangerous capabilities to avoid being deactivated.
method Developed a simple model of strategic deception in sequential decision-making tasks.
result Demonstrated that optimal rational agents exhibit sandbagging behavior.
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full auto…
New approach simulates reputation dynamics using information compression.
problem Malicious communication strategies in reputation networks.
method Uses information compression techniques to simulate social phenomena.
result Emergent phenomena like echo chambers and deception are observed.
The Economist recently reported that infrastructure spending is the largest it is ever been as a share of world GDP. With $22 trillion in projected investments over the next ten years in emerging economies alone, the magazine calls it the "biggest investment boom in history." The efficiency of infrastructure planning a…
The cost-benefit analysis formulates the holy trinity of objectives of project management - cost, schedule, and benefits. As our previous research has shown, ICT projects deviate from their initial cost estimate by more than 10% in 8 out of 10 cases. Academic research has argued that Optimism Bias and Black Swan Blindn…
This paper examines unfair trading practices in NFT markets.
problem Sophisticated actors exploit market inefficiencies for unfair profits.
method Analyzes three types of opportunistic trading strategies.
result Identifies and categorizes unfair trading practices in NFT markets.
"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.
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
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.
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and o…
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…