Search Results for author:
Found 45 papers, 14 papers with code
CERT-ED: Certifiably Robust Text Classification for Edit Distance
With the growing integration of AI in daily life, ensuring the robustness of systems to inference-time attacks is crucial.
Adaptive Data Analysis for Growing Data
In a batched query setting, the asymptotic data requirements of our bound grows with the square-root of the number of adaptive queries, matching prior works' improvement over data splitting for the static setting.
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks.
RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing
Randomized smoothing has shown promising certified robustness against adversaries in classification tasks.
TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs.
Backdoor Attack on Multilingual Machine Translation
Our aim is to bring attention to these vulnerabilities within MNMT systems with the hope of encouraging the community to address security concerns in machine translation, especially in the context of low-resource languages.
It's Simplex! Disaggregating Measures to Improve Certified Robustness
Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calculated size.
Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus.
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness.
RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
When applied to the popular MalConv malware detection model, our smoothing mechanism RS-Del achieves a certified accuracy of 91% at an edit distance radius of 128 bytes.
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity
In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution.
Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes
We also prove that all intersection-closed classes with VC dimension $d$ admit unlabelled compression schemes of size at most $11d$.
Testing the Robustness of Learned Index Structures
To simulate adversarial workloads, we carry out a data poisoning attack on linear regression models that manipulates the cumulative distribution function (CDF) on which the learned index model is trained.
State Selection Algorithms and Their Impact on The Performance of Stateful Network Protocol Fuzzing
In this work, we evaluate an extensive set of state selection algorithms on the same fuzzing platform that is AFLNet, a state-of-the-art fuzzer for network servers.
Improving Robustness with Optimal Transport based Adversarial Generalization
More specifically, by minimizing the WS distance of interest, an adversarial example is pushed toward the cluster of benign examples sharing the same label on the latent space, which helps to strengthen the generalization ability of the classifier on the adversarial examples.
Local Intrinsic Dimensionality Signals Adversarial Perturbations
In this paper, we derive a lower-bound and an upper-bound for the LID value of a perturbed data point and demonstrate that the bounds, in particular the lower-bound, has a positive correlation with the magnitude of the perturbation.
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
The right to erasure requires removal of a user's information from data held by organizations, with rigorous interpretations extending to downstream products such as learned models.
No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees
Our comprehensive empirical evaluation against a state-of-the-art commercial tuning tool demonstrates up to 75% speed-up on shifting and ad-hoc workloads and up to 28% speed-up on static workloads in analytical processing environments.
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation.
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning
In this paper, we show that targeted attacks on black-box NMT systems are feasible, based on poisoning a small fraction of their parallel training data.
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees
Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures.
A Graph Symmetrisation Bound on Channel Information Leakage under Blowfish Privacy
Blowfish privacy is a recent generalisation of differential privacy that enables improved utility while maintaining privacy policies with semantic guarantees, a factor that has driven the popularity of differential privacy in computer science.
Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors
Based on the requirements of fidelity (approximate models to target models) and interpretability (being meaningful to people), we design measurements and evaluate a range of matrix factorization methods with our framework.
Discrete Few-Shot Learning for Pan Privacy
In this paper we present the first baseline results for the task of few-shot learning of discrete embedding vectors for image recognition.
Needle in a Haystack: Label-Efficient Evaluation under Extreme Class Imbalance
Important tasks like record linkage and extreme classification demonstrate extreme class imbalance, with 1 minority instance to every 1 million or more majority instances.
Assessing Centrality Without Knowing Connections
We consider the privacy-preserving computation of node influence in distributed social networks, as measured by egocentric betweenness centrality (EBC).
Legion: Best-First Concolic Testing
Legion incorporates a form of directed fuzzing that we call approximate path-preserving fuzzing (APPFuzzing) to investigate program states selected by MCTS.
d-blink: Distributed End-to-End Bayesian Entity Resolution
Entity resolution (ER; also known as record linkage or de-duplication) is the process of merging noisy databases, often in the absence of unique identifiers.
Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting.
Truth Inference at Scale: A Bayesian Model for Adjudicating Highly Redundant Crowd Annotations
As we show, datasets produced by crowd-sourcing are often not of this type: the data is highly redundantly annotated ($\ge 5$ annotations per instance), and the vast majority of workers produce high quality outputs.
A Note on Bounding Regret of the C$^2$UCB Contextual Combinatorial Bandit
We revisit the proof by Qin et al. (2014) of bounded regret of the C$^2$UCB contextual combinatorial bandit.
Differentially-Private Two-Party Egocentric Betweenness Centrality
We describe a novel protocol for computing the egocentric betweenness centrality of a node when relevant edge information is spread between two mutually distrusting parties such as two telecommunications providers.
Reinforcement Learning for Autonomous Defence in Software-Defined Networking
Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification.
Sampling Without Compromising Accuracy in Adaptive Data Analysis
In this work, we study how to use sampling to speed up mechanisms for answering adaptive queries into datasets without reducing the accuracy of those mechanisms.
Pain-Free Random Differential Privacy with Sensitivity Sampling
Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function.
Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks
Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification.
In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling
Entity resolution (ER) presents unique challenges for evaluation methodology.
Large-Scale Strategic Games and Adversarial Machine Learning
Such high-dimensional decision spaces and big data sets lead to computational challenges, relating to efforts in non-linear optimization scaling up to large systems of variables.
TopicResponse: A Marriage of Topic Modelling and Rasch Modelling for Automatic Measurement in MOOCs
This paper explores the suitability of using automatically discovered topics from MOOC discussion forums for modelling students' academic abilities.
MOOCs Meet Measurement Theory: A Topic-Modelling Approach
Such models infer latent skill levels by relating them to individuals' observed responses on a series of items such as quiz questions.
Principled Graph Matching Algorithms for Integrating Multiple Data Sources
In the most common case of matching two sources, it is often desirable for the final matching to be one-to-one (a record may be matched with at most one other); members of the database and statistical record linkage communities accomplish such matchings in the final stage by weighted bipartite graph matching on similarity scores.
Security Evaluation of Support Vector Machines in Adversarial Environments
Support Vector Machines (SVMs) are among the most popular classification techniques adopted in security applications like malware detection, intrusion detection, and spam filtering.
Bounding Embeddings of VC Classes into Maximum Classes
The most promising approach to positively resolving the conjecture is by embedding general VC classes into maximum classes without super-linear increase to their VC dimensions, as such embeddings would extend the known compression schemes to all VC classes.
