Search Results for author:
Found 37 papers, 7 papers with code
Concept-based Analysis of Neural Networks via Vision-Language Models
The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures.
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
Textual backdoor attacks pose significant security threats.
Calibration and Correctness of Language Models for Code
Our contributions will lead to better-calibrated decision-making in the current use of code generated by language models, and offers a framework for future research to further improve calibration methods for generative models in Software Engineering.
Direct Amortized Likelihood Ratio Estimation
Our estimator is simple to train and estimates the likelihood ratio using a single forward pass of the neural estimator.
math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories
As artificial intelligence (AI) gains greater adoption in a wide variety of applications, it has immense potential to contribute to mathematical discovery, by guiding conjecture generation, constructing counterexamples, assisting in formalizing mathematics, and discovering connections between different mathematical areas, to name a few.
Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving
We posit that we can use the satisfiability modulo theory (SMT) solvers as deductive reasoning engines to analyze the generated solutions from the LLMs, produce counterexamples when the solutions are incorrect, and provide that feedback to the LLMs exploiting the dialog capability of instruct-trained LLMs.
Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions
We provide an empirical demonstration of the fragility of ResNet-like models to Gaussian noise perturbations, where the model performance deteriorates sharply and its F1-score drops to near insignificance at 0. 008 with a Gaussian noise of only 0. 5 standard deviation.
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models
We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization).
Measuring Classification Decision Certainty and Doubt
Quantitative characterizations and estimations of uncertainty are of fundamental importance in optimization and decision-making processes.
On the Robustness of AlphaFold: A COVID-19 Case Study
To measure the robustness of the predicted structures, we utilize (i) the root-mean-square deviation (RMSD) and (ii) the Global Distance Test (GDT) similarity measure between the predicted structure of the original sequence and the structure of its adversarially perturbed version.
Design of Unmanned Air Vehicles Using Transformer Surrogate Models
In this paper, we develop an AI Designer that synthesizes novel UAV designs.
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data
Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution.
Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions
Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning.
Multiple Testing Framework for Out-of-Distribution Detection
While a number of tests for OOD detection have been proposed in prior work, a formal framework for studying this problem is lacking.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Principal Manifold Flows
In this paper we characterize the geometric structure of flows using principal manifolds and understand the relationship between latent variables and samples using contours.
Detecting out-of-context objects using contextual cues
GCRN consists of two separate graphs to predict object labels based on the contextual cues in the image: 1) a representation graph to learn object features based on the neighboring objects and 2) a context graph to explicitly capture contextual cues from the neighboring objects.
Ranked #1 on
Anomaly Detection
on COCO-OOC
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection.
Dual-Key Multimodal Backdoors for Visual Question Answering
This is challenging for the attacker as the detector can distort or ignore the visual trigger entirely, which leads to models where backdoors are over-reliant on the language trigger.
Trigger Hunting with a Topological Prior for Trojan Detection
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks.
Physical System Design Using Hamiltonian Monte Carlo over Learned Manifolds
We use deep generative models to learn a manifold of the valid design space, followed by Hamiltonian Monte Carlo (HMC) with simulated annealing to explore and optimize design over the learned manifold, producing a diverse set of optimal designs.
Protein Folding Neural Networks Are Not Robust
We define the robustness measure for the predicted structure of a protein sequence to be the inverse of the root-mean-square distance (RMSD) in the predicted structure and the structure of its adversarially perturbed sequence.
Detecting OODs as datapoints with High Uncertainty
We demonstrate the difference in the detection ability of these techniques and propose an ensemble approach for detection of OODs as datapoints with high uncertainty (epistemic or aleatoric).
MISA: Online Defense of Trojaned Models using Misattributions
Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways.
Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs
Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs.
Robust Ensembles of Neural Networks using Itô Processes
We exploit this connection and the theory of stochastic dynamical systems to construct a novel ensemble of Itô processes as a new deep learning representation that is more robust than classical residual networks.
Detecting Trojaned DNNs Using Counterfactual Attributions
We target the problem of detecting Trojans or backdoors in DNNs.
An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
We present a new extension of Fano's inequality and employ it to theoretically establish that the probability of success for a membership inference attack on a deep neural network can be bounded using the mutual information between its inputs and its activations.
Attribution-Based Confidence Metric For Deep Neural Networks
These experiments demonstrate the effectiveness of the ABC metric to make DNNs more trustworthy and resilient.
Estimating the Density of States of Boolean Satisfiability Problems on Classical and Quantum Computing Platforms
Given a Boolean formula $\phi(x)$ in conjunctive normal form (CNF), the density of states counts the number of variable assignments that violate exactly $e$ clauses, for all values of $e$.
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
These defenses rely on the assumption that data lie in a manifold of a lower dimension than the input space.
Attribution-driven Causal Analysis for Detection of Adversarial Examples
We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood.
TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time.
Trusted Neural Networks for Safety-Constrained Autonomous Control
Experiments using our first approach of a multi-headed TNN model, on a dataset generated by a customized version of TORCS, show that (1) adding safety constraints to a neural network model results in increased performance and safety, and (2) the improvement increases with increasing importance of the safety constraints.
Learning Task Specifications from Demonstrations
In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications.
Output Range Analysis for Deep Neural Networks
We demonstrate the effectiveness of the proposed approach for verification of NNs used in automated control as well as those used in classification.
A Theory of Formal Synthesis via Inductive Learning
In this paper, we present a theoretical framework for formal inductive synthesis.
Are There Good Mistakes? A Theoretical Analysis of CEGIS
The history bounded counterexample used in any iteration of CEGIS is bounded by the examples used in previous iterations of inductive synthesis.
