This study investigates security vulnerabilities of SNNs and compares them to DNNs.
problem Investigating security vulnerabilities of Spiking Neural Networks (SNNs) compared to Deep Neural Networks (DNNs).
method Comparative study of security vulnerabilities, novel black-box attack methodology for SNNs.
result Proposed and evaluated a novel black-box attack methodology for SNNs.
Explores security challenges of machine learning in real-world systems.
problem Vulnerabilities in machine learning models deployed in safety-critical systems.
method Broadens systems security view of ML vulnerabilities, identifies novel challenges, proposes mitigation suggestions.
result Highlights novel challenges and proposes mitigation strategies for securing ML systems.
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.
Devign uses graph neural networks to identify vulnerabilities efficiently.
problem Challenging and tedious process of identifying vulnerabilities in software systems.
method Devign employs a graph neural network to classify graph-level vulnerabilities using comprehensive code semantic representations.
result Devign significantly outperforms state-of-the-art models in vulnerability identification.
The paper evaluates methods for explaining deep learning in security.
problem Understanding the predictions of deep learning models in security applications.
method Developed criteria to compare and evaluate six explanation methods.
result Significant differences exist between the methods, leading to recommendations.
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…
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.
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.
Securely trains neural networks remotely with deep learning's flaws.
problem Secure and efficient training of neural networks over unsecured channels.
method Leverages deep learning's weaknesses for secure training.
result Efficient and secure training of neural networks remotely.
In this paper are presented methods of impact analysis on informatics system security accidents, qualitative and quantitative methods, starting with risk and informational system security definitions. It is presented the relationship between the risks of exploiting vulnerabilities of security system, security level of …
Thousands of security vulnerabilities are discovered in production software each year, either reported publicly to the Common Vulnerabilities and Exposures database or discovered internally in proprietary code. Vulnerabilities often manifest themselves in subtle ways that are not obvious to code reviewers or the develo…
Bin2vec learns executable program representations for security tasks.
problem Manual rule and heuristic definition for binary program analysis is tedious and time-consuming.
method Bin2vec uses Graph Convolutional Networks (GCN) on computational program graphs.
result Improvement over state-of-the-art methods for binary analysis tasks.
SLIP secures LLMs on edge devices by splitting computation and protecting sensitive parts.
problem Protecting LLMs on edge devices from theft and unauthorized use.
method SLIP uses matrix decomposition to split model computation between secure and vulnerable resources, ensuring zero accuracy degradation and minimal latency.
result SLIP is the first practical, secure hybrid protocol for protecting LLMs on edge devices.
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.
Deep neural networks are vulnerable to adversarial attacks in time series classification.
problem Vulnerability of deep learning models to adversarial time series examples.
method Proposed adversarial attack mechanisms to add noise to input time series.
result Current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks.
Framework detects cyber threats from Twitter tweets.
problem Time-consuming manual extraction of cyber threat intelligence.
method Novelty detection model trained on CVE data.
result F1-score of 0.643 for classifying cyber threat tweets.
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.
Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are increasingly difficult and expensive. This work aims to develop secu…
Improved security of smart contracts by classifying them into four categories.
problem Detecting and classifying vulnerabilities in smart contracts efficiently.
method Used AWD-LSTM for multi-class classification, addressing class imbalance.
result Achieved a weighted average Fbeta score of 90.0%.
BadGD identifies gradient descent vulnerabilities through strategic backdoor attacks.
problem Gradient descent vulnerabilities through malicious data manipulation.
method Introduces Max RiskWarp, Max GradWarp, and Max GradDistWarp triggers to exploit gradient descent.
result Demonstrates how malicious triggers can significantly alter loss landscapes and gradient calculations.
Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities are known and users quickly install those patches as soon as they are available…
Most of the existing solutions to enterprise threat management are preventive approaches prescribing means to prevent policy violations with varying degrees of success. In this paper we consider the complementary scenario where a number of security violations have already occurred, or security threats, or vulnerabiliti…
Paper tackles model vulnerabilities by reconstructing training data.
problem Reconstructing training data from model parameters poses a security risk.
method Developed a mathematical framework and score matching method for both Bayesian and non-Bayesian models.
result First score matching framework for reconstructing data in Bayesian models.
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. 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.
Research creates a taxonomy to bridge AI security and regulatory gaps.
problem Disciplinary disconnect between technical and legal teams in AI risk assessment.
method Developed an AI System Threat Vector Taxonomy with 9 domains and 53 sub-threats.
result Empirically validated and aligned with ISO/IEC 42001 controls and NIST AI RMF functions.
This paper examines SVB's failure and its impact on bank stocks.
problem SVB failure and its contagion effects on bank stocks.
method Analyzed bank-specific vulnerabilities and stock performance.
result Uninsured deposits and unrealized losses were key factors in SVB's impact.
While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and sophistication of attacks, has prompted the need for a data driven solution, wit…
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.
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.
The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule or signature based methods cannot. However, classifiers operating in adversarial …
Locality-sensitive hashing speeds up web app security testing.
problem Challenges in crawling Rich Internet Applications (RIAs) due to state similarity.
method Uses MinHash sketches to analyze DOM structures and estimate similarity.
result Successfully scans RIAs that traditional crawling methods cannot.
Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to evade, b) easier to detect changes in the data distribution over time, and c) be ab…
Paper shows attacks on transfer learning models without target-specific info.
problem Security vulnerability in transfer learning models.
method Brute force attack on pre-trained models without target-specific data.
result Demonstrates effective and efficient attacks on transfer learning models.
Wrist movements can reveal digits, posing security risks.
problem Security vulnerabilities in wrist wearable devices.
method Machine learning model trained on wrist movement data.
result 100% accuracy in predicting digits via wrist movement.
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.
With a large number of sensors and control units in networked systems, distributed support vector machines (DSVMs) play a fundamental role in scalable and efficient multi-sensor classification and prediction tasks. However, DSVMs are vulnerable to adversaries who can modify and generate data to deceive the system to mi…
Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a growing interest in both research and industrial communities in the promising potentials of this paradigm. The list of current and envisioned applications of deep RL ranges from autonomous navigation and robotics to control applicatio…
Nowadays, machine learning based Automatic Speech Recognition (ASR) technique has widely spread in smartphones, home devices, and public facilities. As convenient as this technology can be, a considerable security issue also raises -- the users' speech content might be exposed to malicious ASR monitoring and cause seve…
Deep-CAPTCHA cracks visual CAPTCHAs using deep learning.
problem Cracking visual CAPTCHAs to assess vulnerabilities.
method Developed a Convolutional Neural Network (Deep-CAPTCHA) to solve numerical and alphanumeric CAPTCHAs.
result Cracking accuracy of 98.94% and 98.31% for numerical and alphanumeric datasets respectively.
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.
Secure sum outperforms homomorphic encryption in collaborative deep learning.
problem Training deep learning models on private data from multiple parties without revealing the data.
method Used a secure sum protocol in conjunction with default secure channels.
result Secure sum protocol provides superior properties in terms of collusion-resistance and runtime.
Adversarial objects can fool LiDAR-based autonomous driving systems.
problem Vulnerability of LiDAR-based autonomous driving systems to adversarial attacks.
method Optimization-based approach LiDAR-Adv to generate adversarial objects.
result LiDAR-based autonomous driving systems are vulnerable to adversarial attacks.
A new federated learning method protects privacy in mobile crowdsensing.
problem Data and model privacy protection in federated extreme gradient boosting for mobile crowdsensing.
method Secret sharing based federated learning architecture FedXGB.
result FedXGB achieves less than 1% accuracy loss while preserving model privacy.
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…
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 attacks CNNs in EEG BCIs with adversarial examples.
problem Vulnerability of CNN classifiers in EEG-based BCIs.
method UFGSM to attack three popular CNN classifiers in BCIs.
result Demonstrates effectiveness of adversarial attacks on CNNs in BCIs.
Bayesian methods improve adversarial machine learning robustness.
problem Improving machine learning systems' security against adversarial manipulation.
method Integrating Bayesian perspectives to relax unrealistic assumptions in game-theoretic models.
result Bayesian approach provides more robust inferences about opponent's beliefs and interests.