Search Results for author:
Found 23 papers, 11 papers with code
LLM-Safety Evaluations Lack Robustness
In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
While it is often easy to craft prompts that yield a substantial likelihood for the affirmative response, the attacked model frequently does not complete the response in a harmful manner.
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
In this study, we propose a novel gradient-based approach to representation engineering and use it to identify refusal directions.
Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance
Such signals can be categorized as inherently directed, for example, the water flow in a pipe network, and undirected, like the diameter of a pipe.
Relaxing Graph Transformers for Adversarial Attacks
Existing studies have shown that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks.
Explainable Graph Neural Networks Under Fire
In this paper we demonstrate that these explanations can unfortunately not be trusted, as common GNN explanation methods turn out to be highly susceptible to adversarial perturbations.
Spatio-Spectral Graph Neural Networks
Motivated by these limitations, we propose Spatio-Spectral Graph Neural Networks (S$^2$GNNs) -- a new modeling paradigm for Graph Neural Networks (GNNs) that synergistically combines spatially and spectrally parametrized graph filters.
Ranked #5 on
Graph Classification
on Peptides-func
Attacking Large Language Models with Projected Gradient Descent
Current LLM alignment methods are readily broken through specifically crafted adversarial prompts.
Poisoning $\times$ Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks
It is well-known that deep learning models are vulnerable to small input perturbations.
On the Adversarial Robustness of Graph Contrastive Learning Methods
Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks.
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required.
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.
Revisiting Robustness in Graph Machine Learning
Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure.
Transformers Meet Directed Graphs
Transformers were originally proposed as a sequence-to-sequence model for text but have become vital for a wide range of modalities, including images, audio, video, and undirected graphs.
Ranked #1 on
Graph Property Prediction
on ogbg-code2
Are Defenses for Graph Neural Networks Robust?
A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs).
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
To remedy this, we propose novel gray-box certificates that exploit the message-passing principle of GNNs: We randomly intercept messages and carefully analyze the probability that messages from adversarially controlled nodes reach their target nodes.
On the Robustness and Anomaly Detection of Sparse Neural Networks
The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world.
Winning the Lottery Ahead of Time: Efficient Early Network Pruning
Pruning, the task of sparsifying deep neural networks, received increasing attention recently.
Robustness of Graph Neural Networks at Scale
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications.
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
GPN outperforms existing approaches for uncertainty estimation in the experiments.
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
Specifically, most datasets only capture a simpler subproblem and likely suffer from spurious features.
Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions
Uncertainty awareness is crucial to develop reliable machine learning models.
Reliable Graph Neural Networks via Robust Aggregation
Perturbations targeting the graph structure have proven to be extremely effective in reducing the performance of Graph Neural Networks (GNNs), and traditional defenses such as adversarial training do not seem to be able to improve robustness.
