Search Results for author:
Found 25 papers, 7 papers with code
Cognitive Overload Attack:Prompt Injection for Long Context
We applied the principles of Cognitive Load Theory in LLMs and empirically validate that similar to human cognition, LLMs also suffer from cognitive overload a state where the demand on cognitive processing exceeds the available capacity of the model, leading to potential errors.
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
In this paper, we introduce a new black-box attack vector called the \emph{Sandwich attack}: a multi-language mixture attack, which manipulates state-of-the-art LLMs into generating harmful and misaligned responses.
TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes
Our results indicate that the TaCo method impresses GPT-4 with an 82\% score for a low-resource language in the Vicuna Benchmark dataset, doubling the performance in contrast to instruction tuning alone.
Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events
Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions.
Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)
Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior.
Stochastic Induction of Decision Trees with Application to Learning Haar Tree
Experimentally, the algorithm is compared with several other related state-of-the-art decision tree learning methods, including the baseline non-stochastic approach.
Synthetic Reduced Nearest Neighbor Model for Regression
This algorithm is comprised of two steps: (1) The assignment step, where assignments of the samples to each centroid is found and the target response (i. e., prediction) of each centroid is determined; and (2) the update/centroid step, where each centroid is updated such that the loss function of the entire model is minimized.
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors
Through extensive experimental analysis, we demonstrate that (i) the proposed attack technique can deteriorate the accuracy of several models drastically, and (ii) under the proposed attack, the proposed defense technique significantly outperforms other conventional machine learning models in recovering the accuracy of the targeted model.
Adversarial Attacks on Deep Algorithmic Trading Policies
Deep Reinforcement Learning (DRL) has become an appealing solution to algorithmic trading such as high frequency trading of stocks and cyptocurrencies.
Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification
The rampant integration of social media in our every day lives and culture has given rise to fast and easier access to the flow of information than ever in human history.
Cultural Vocal Bursts Intensity Prediction
Emotion Recognition
+4
Founding The Domain of AI Forensics
With the widespread integration of AI in everyday and critical technologies, it seems inevitable to witness increasing instances of failure in AI systems.
A Novel Approach for Detection and Ranking of Trendy and Emerging Cyber Threat Events in Twitter Streams
We present a new machine learning and text information extraction approach to detection of cyber threat events in Twitter that are novel (previously non-extant) and developing (marked by significance with respect to similarity with a previously detected event).
RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies
This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space.
Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal performance of the policy.
Adversarial Exploitation of Policy Imitation
This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies.
Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations.
Emergence of Addictive Behaviors in Reinforcement Learning Agents
This paper presents a novel approach to the technical analysis of wireheading in intelligent agents.
TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles
This paper presents TrolleyMod v1. 0, an open-source platform based on the CARLA simulator for the collection of ethical decision-making data for autonomous vehicles.
The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning
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.
Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise
Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples.
Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles
With the rapidly growing interest in autonomous navigation, the body of research on motion planning and collision avoidance techniques has enjoyed an accelerating rate of novel proposals and developments.
A Psychopathological Approach to Safety Engineering in AI and AGI
The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety.
Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger
Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations.
Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks
Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples.
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
An adversarial example library for constructing attacks, building defenses, and benchmarking both
