Related papers: If there's a Trigger Warning, then where's the Tri…
Bug reports are common artefacts in software development. They serve as the main channel for users to communicate to developers information about the issues that they encounter when using released versions of software programs. In the…
This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…
Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological…
Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…
Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…
Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…
The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…
Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data. We present a methodology for programmatically identifying and removing…
Nested named entity recognition (NER) aims to identify the entity boundaries and recognize categories of the named entities in a complex hierarchical sentence. Some works have been done using character-level, word-level, or lexicon-level…
Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot. Despite its usefulness, this application…
With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…
Adversarial input image perturbation attacks have emerged as a significant threat to machine learning algorithms, particularly in image classification setting. These attacks involve subtle perturbations to input images that cause neural…
Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep…
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…
We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…
In functional programming languages, the classic form of annotation is a single type constraint on a term. Intersection types add complications: a single term may have to be checked several times against different types, in different…
Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data…
Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…
Producing the required amounts of training data for machine learning and NLP tasks often involves human annotators doing very repetitive and monotonous work. In this paper, we present and evaluate our novel annotation framework DALPHI,…
Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…