This paper discusses adversarial attacks on cyber security systems using machine learning.
problem Adversarial attacks limit the use of machine learning in cyber security.
method Characterizes adversarial attack methods and their applications in cyber security.
result Highlights unique challenges and future research directions for adversarial attacks in cyber security.
New method defends machine learning models from black-box attacks.
problem Protecting machine learning models from black-box transfer attacks.
method Randomized ensemble technique with provable security guarantee.
result Empirical evidence of security for random binary classifiers.
This paper reviews adversarial attacks on ML and DL models.
problem Adversarial attacks on ML and DL models.
method Review of existing adversarial attacks and perturbations.
result Comprehensive understanding of adversarial security attacks on ML and DL.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
New model improves classifier security against evasion attacks by selecting features.
problem Security of machine learning classifiers against evasion attacks.
method Adversary-aware feature selection model incorporating specific adversary assumptions.
result Classifier security worsens with feature selection, but new model improves it.
secml is a Python library for secure and explainable machine learning.
problem Evaluate and understand security and explainability of machine learning models.
method Implement attacks and explainability methods for various algorithms.
result Demonstrates how quickly models fail under adversarial perturbations and visualizes influential features.
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
New study analyzes security of neural network data reconstruction attacks.
problem Data reconstruction attacks pose a threat to private training data.
method Analyzes security boundary of data reconstruction attacks via neuron exclusivity state.
result Characterizes insecure/secure boundary of data reconstruction attacks.
Investigates the cost-effectiveness of security features in smart card chips.
problem Costs of adding security features to smart card chips.
method Examines production phases, costs, and security features.
result Security features are worth the cost due to potential damages from attacks.
New attacks reduce bad queries in black-box classifiers, improving effectiveness.
problem Evasion attacks often issue many bad queries, which are costly.
method Design new attacks that minimize bad queries while increasing non-bad queries.
result Reduces the number of bad queries by 1.5-7.3 times, improving attack effectiveness.
Deep RL enhances cyber security through adaptive, responsive, and scalable defenses.
problem Complex, dynamic cyber attacks require adaptive and scalable security solutions.
method Incorporates deep learning into traditional RL for cyber defense.
result Demonstrates the potential of DRL in solving high-dimensional cyber defense problems.
Study assesses how much security restaking protocols need to pay for.
problem Determining the optimal security level for restaking protocols using token incentives.
method Expanding a model by Durvasula and Roughgarden to include strategic attackers and node operators, constructing an approximation algorithm for token-based incentives.
result Restaking protocols can be secure with proper incentive management, even against strategic adversaries.
Survey examines ML for IoT security, addressing new challenges.
problem IoT security challenges due to rapid growth and diverse attacks.
method Comprehensive literature review of ML-based security solutions.
result ML provides dynamic and efficient security for IoT.
This work develops secure distributed algorithms for machine learning to protect against data poisoning and network attacks.
problem Vulnerability of distributed machine learning algorithms to cyber threats.
method Game-theoretic framework to capture conflicting goals of a learner and an attacker, iterative distributed algorithm.
result Distributed SVM is prone to fail in different types of attacks, with impact depending on network structure and attack capabilities.
Defense against small image patches using occlusions.
problem Vulnerability of deep learning to small adversarial patches.
method Partially occlude image around each patch location.
result Certified security against patch attacks of a certain size.
In machine learning (ML) security, attacks like evasion, model stealing or membership inference are generally studied in individually. Previous work has also shown a relationship between some attacks and decision function curvature of the targeted model. Consequently, we study an ML model allowing direct control over t…
Paper proposes efficient privacy-preserving matrix encryption for secure collaborative learning against malicious adversaries.
problem Secure collaborative learning of sensitive data across different agencies is challenging with malicious adversaries.
method The paper applies matrix encryption to secure data against chosen plaintext attack, known plaintext attack, and collusion attack, achieving local differential privacy and high computation efficiency.
result The proposed schemes are computationally efficient and secure against malicious adversaries compared to existing techniques.
New attack method improves neural network security.
problem Vulnerability of deep neural networks to adversarial attacks.
method Ensemble adversarial attack with long-term gradient memory.
result Enhanced robustness against adversarial attacks.
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.
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.
This work surveys attacks and defenses on edge neural networks.
problem Security challenges of edge neural networks due to their compute and memory intensity, data-independence, and privacy risks.
method Taxonomy of attacks and defenses on edge-deployed neural networks.
result New security considerations and approaches are needed for edge DNNs.
The paper certifies decision trees against evasion attacks using program analysis.
problem Vulnerability of decision tree models to evasion attacks by maliciously crafted perturbations.
method Transform decision trees into imperative programs for program analysis, leveraging abstract interpretation.
result Soundly verifies security guarantees of decision tree models, yielding minimal false positives.
Paper discusses imperceptible attacks on tabular data models.
problem Security of machine learning models on tabular data.
method Formalizes imperceptibility of adversarial attacks, proposes an approach to generate imperceptible adversarial examples.
result Demonstrates ability to generate imperceptible adversarial examples with high fooling rate.
Adversarial edit attacks improve machine learning model security for tree data.
problem Improving security of machine learning models for tree-structured data.
method Extends adversarial attacks to tree-structured data using tree edit distance and black-box queries.
result Many tree classifiers can be effectively attacked, demonstrating the vulnerability of these models.
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. Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for antivirus systems. However, the suitability of clustering algorithms for security-sensitive settings has been recently questioned by showing tha…
Cronus securely transfers model parameters to protect federated learning from poisoning attacks.
problem Federated learning's privacy and security issues, especially with large models.
method Cronus uses black-box knowledge transfer to reduce parameter dimensions and control information leakage.
result Cronus is the only secure federated learning method against poisoning attacks.
CheckNet verifies neural network inference on untrusted devices.
problem Ensuring secure and tamper-proof inference on untrusted devices.
method A checksum-based approach for neural network inference verification.
result Excellent attack detection and success bounds on various models.
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
New method uses model's generalization gap to predict membership inference attacks.
problem Predicting membership inference attacks on machine learning models.
method Uses the model's generalization gap as a metric to estimate the vulnerability to membership inference attacks.
result Demonstrates that the model's generalization gap provides an upper bound on MIA security.
Researchers develop methods to protect reinforcement learning and control systems from policy poisoning attacks.
problem Attacks on reinforcement learning and control systems that manipulate learned policies.
method Unified framework for solving policy poisoning attacks, demonstrating global optimality and feasibility.
result Policy poisoning attacks are feasible and can be defended with a convex optimization approach.
New security patch for object tracking in self-driving cars mitigates vulnerabilities.
problem Vulnerability of object tracking in self-driving cars, especially Kalman Filter-based trackers.
method Adaptive strategy to balance focus on observations and predictions based on deviation anomaly index.
result Certified effectiveness against a generalized hijacking attack model.
The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the eno…
Paper analyzes InstaHide's security, recovering all private images with provable guarantee.
problem Protecting privacy of training data in neural networks.
method Unified framework to understand and analyze attacks on InstaHide, presenting a new algorithm to recover all private images with provable guarantee.
result InstaHide is computationally secure but not information-theoretically secure when mixing two private images.
Article evaluates AI security threats and proposes multiple measures.
problem Threats to AI integrity and security.
method Literature review, analysis of AI supply chain, discussion of mitigations.
result Multiple protective measures are necessary for AI security.
Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings r…
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. This study examines LiDAR spoofing attacks on autonomous vehicle perception.
problem Security vulnerabilities in LiDAR-based perception systems in autonomous driving.
method Formulated as an optimization problem, designed input perturbation and objective functions, combined optimization and global sampling.
result Attack success rates improved to around 75% through strategic input perturbation.
Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised by attackers both at training and test time. Machine learning systems are especi…
Study on how many queries an adversary needs to make to match the best attack in white-box model.
problem Query complexity of adversarial attacks in machine learning models.
method Investigates the number of queries required for an adversary to match the best possible attack in the white-box model, using entropy of decision boundaries as a measure.
result Lower bound on the number of queries required for an adversary to match the best possible attack in the white-box model.
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.
Attackers can poison environments to force RL agents to follow target policies.
problem Security threat to reinforcement learning where attackers manipulate environments to force agents into following target policies.
method Optimization framework for finding optimal stealthy attacks under different measures of attack cost.
result Attackers can easily succeed in teaching any target policy to RL agents under mild conditions.
Survey on securing ML for healthcare, addressing privacy and robustness issues.
problem Security and robustness challenges in healthcare ML/DL applications.
method Overview of security and privacy methods for ML in healthcare.
result Discussion of current research challenges and future directions.
RL models improve target control in SSGs for security applications.
problem Improving RL algorithms for target control in SSGs.
method Investigates improvements to target representations in RL algorithms.
result Enhanced RL models control targets better in SSGs.
Paper defends diffusion models from membership inference attacks using Langevin dynamics.
problem Defending diffusion models against membership inference attacks.
method Uses critically-damped higher-order Langevin dynamics with auxiliary variables.
result Demonstrates improved resistance to membership inference attacks through theoretical investigation and validation.
Paper proposes NeuroAttack to undermine SNNs security through bit-flips.
problem Security and reliability issues in SNNs.
method Cross-layer attack exploiting low-level reliability issues via adversarial input noise.
result Serious integrity threat to SNNs and DNNs.
Stochastic defense improves natural classifiers against adversarial attacks.
problem Vulnerability of deep networks to adversarial attacks.
method Long-run MCMC sampling with Energy-Based Model for adversarial purification.
result Balancing memoryless and metastable behavior leads to effective purification and robust classification.
Research shows filtering reduces predictability of cyber-attacks.
problem Predicting cyber-attacks from incomplete data.
method Combining external data with machine learning algorithms to learn indicators of cyber-attacks.
result The process of filtering reduces the predictability of cyber-attacks.