Search Results for author:
Found 37 papers, 10 papers with code
Fault Tolerant Neural Control Barrier Functions for Robotic Systems under Sensor Faults and Attacks
Control barrier function (CBF)-based approaches have been proposed to guarantee the safety of robotic systems.
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
In this paper, we propose a novel ASCII art-based jailbreak attack and introduce a comprehensive benchmark Vision-in-Text Challenge (ViTC) to evaluate the capabilities of LLMs in recognizing prompts that cannot be solely interpreted by semantics.
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Our results show that SafeDecoding significantly reduces the attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries.
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors.
Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is unexplored.
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Moreover, we show that LLMs endowed with stronger reasoning capabilities exhibit higher susceptibility to BadChain, exemplified by a high average attack success rate of 97. 0% across the six benchmark tasks on GPT-4.
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
Our results show that the global model learned with Brave in the presence of adversaries achieves comparable classification accuracy to a global model trained in the absence of any adversary.
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
Successful exploits of the identified vulnerabilities result in the users receiving responses tailored to the intent of a threat initiator.
MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
An adversary carrying out a backdoor attack embeds a predefined perturbation called a trigger into a small subset of input samples and trains the DNN such that the presence of the trigger in the input results in an adversary-desired output class.
Risk-Aware Distributed Multi-Agent Reinforcement Learning
We then propose a distributed MARL algorithm called the CVaR QD-Learning algorithm, and establish that value functions of individual agents reaches consensus.
LDL: A Defense for Label-Based Membership Inference Attacks
Overfitted models have been shown to be susceptible to query-based attacks such as membership inference attacks (MIAs).
Game of Trojans: A Submodular Byzantine Approach
The results show that (i) with Submodular Trojan algorithm, the adversary needs to embed a Trojan trigger into a very small fraction of samples to achieve high accuracy on both Trojan and clean samples, and (ii) the MM Trojan algorithm yields a trained Trojan model that evades detection with probability 1.
A Natural Language Processing Approach for Instruction Set Architecture Identification
Empirical evaluations show that using our byte-level features in ML-based ISA identification results in an 8% higher accuracy than the state-of-the-art features based on byte-histograms and byte pattern signatures.
Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning
We term this category of attacks multi-target backdoor attacks.
Privacy-Preserving Reinforcement Learning Beyond Expectation
Through empirical evaluations, we highlight a privacy-utility tradeoff and demonstrate that the RL agent is able to learn behaviors that are aligned with that of a human user in the same environment in a privacy-preserving manner
Shaping Advice in Deep Reinforcement Learning
We design two algorithms- Shaping Advice in Single-agent reinforcement learning (SAS) and Shaping Advice in Multi-agent reinforcement learning (SAM).
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning
In this paper, we introduce Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning (AREL) to address these two challenges.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
A Game-Theoretic Framework for Controlled Islanding in the Presence of Adversaries
In this paper, we study the controlled islanding problem of a power system under disturbances introduced by a malicious adversary.
Reinforcement Learning Beyond Expectation
In this paper, we consider a setting where an autonomous agent has to learn behaviors in an unknown environment.
Shaping Advice in Deep Multi-Agent Reinforcement Learning
We observe that using SAM results in agents learning policies to complete tasks faster, and obtain higher rewards than: i) using sparse rewards alone; ii) a state-of-the-art reward redistribution method.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Safety-Critical Online Control with Adversarial Disturbances
We propose an iterative approach to the synthesis of the controller by solving a modified discrete-time Riccati equation.
Stochastic Dynamic Information Flow Tracking Game using Supervised Learning for Detecting Advanced Persistent Threats
Our game model has imperfect information as the players do not have information about the actions of the opponent.
Computer Science and Game Theory Cryptography and Security
FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback
The output of the feedback neural network is converted to a shaping reward that is augmented to the reward provided by the environment.
Are Odds Really Odd? Bypassing Statistical Detection of Adversarial Examples
In this paper, we first develop a classifier-based adaptation of the statistical test method and show that it improves the detection performance.
Potential-Based Advice for Stochastic Policy Learning
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies.
Dropping Pixels for Adversarial Robustness
Deep neural networks are vulnerable against adversarial examples.
Assessing Shape Bias Property of Convolutional Neural Networks
In order to conduct large scale experiments, we propose using the model accuracy on images with reversed brightness as a metric to evaluate the shape bias property.
Semantic Adversarial Examples
This property is used by several defense methods to counter adversarial examples by applying denoising filters or training the model to be robust to small perturbations.
Attacking Automatic Video Analysis Algorithms: A Case Study of Google Cloud Video Intelligence API
At the end, we propose introducing randomness to video analysis algorithms as a countermeasure to our attacks.
Google's Cloud Vision API Is Not Robust To Noise
For example, an adversary can bypass an image filtering system by adding noise to inappropriate images.
Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos
For this, we select an image, which is different from the video content, and insert it, periodically and at a very low rate, into the video.
On the Limitation of Convolutional Neural Networks in Recognizing Negative Images
To this end, we evaluate CNNs on negative images, since they share the same structure and semantics as regular images and humans can classify them correctly.
Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars.
Deceiving Google's Perspective API Built for Detecting Toxic Comments
In this paper, we propose an attack on the Perspective toxic detection system based on the adversarial examples.
Learning Temporal Dependence from Time-Series Data with Latent Variables
We consider the setting where a collection of time series, modeled as random processes, evolve in a causal manner, and one is interested in learning the graph governing the relationships of these processes.
Group Event Detection with a Varying Number of Group Members for Video Surveillance
This paper presents a novel approach for automatic recognition of group activities for video surveillance applications.
Activity Recognition Using A Combination of Category Components And Local Models for Video Surveillance
This paper presents a novel approach for automatic recognition of human activities for video surveillance applications.
