Adversarial Text
33 papers with code • 0 benchmarks • 2 datasets
Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.
Benchmarks
These leaderboards are used to track progress in Adversarial Text
Libraries
Use these libraries to find Adversarial Text models and implementationsLatest papers
TAPE: Assessing Few-shot Russian Language Understanding
Recent advances in zero-shot and few-shot learning have shown promise for a scope of research and practical purposes.
SemAttack: Natural Textual Attacks via Different Semantic Spaces
In particular, SemAttack optimizes the generated perturbations constrained on generic semantic spaces, including typo space, knowledge space (e. g., WordNet), contextualized semantic space (e. g., the embedding space of BERT clusterings), or the combination of these spaces.
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks
Adversarial attacks are a major challenge faced by current machine learning research.
Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformers
The detection of computer-generated text is an area of rapidly increasing significance as nascent generative models allow for efficient creation of compelling human-like text, which may be abused for the purposes of spam, disinformation, phishing, or online influence campaigns.
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text
In terms of misclassified texts, a classifier handles the texts with both incorrect predictions and adversarial texts, which are generated to fool the classifier, which is called a victim.
Semantic-Preserving Adversarial Text Attacks
In this paper, we propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models.
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation
We present, MATE-KD, a novel text-based adversarial training algorithm which improves the performance of knowledge distillation.
Persistent Anti-Muslim Bias in Large Language Models
It has been observed that large-scale language models capture undesirable societal biases, e. g. relating to race and gender; yet religious bias has been relatively unexplored.
Generating Natural Language Attacks in a Hard Label Black Box Setting
Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model.
Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples
We study the behavior of several black-box search algorithms used for generating adversarial examples for natural language processing (NLP) tasks.