# Task-Agnostic Detector for Insertion-Based Backdoor Attacks

arXiv: https://arxiv.org/abs/2403.17155 · HTML: https://mlsanity.com/paper/2403.17155/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 68 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://mlsanity.com/paper/2105.12400/) (2021)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models](https://mlsanity.com/paper/2103.15543/) (2021)
- [RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models](https://mlsanity.com/paper/2110.07831/) (2021)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)
- [T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification](https://mlsanity.com/paper/2103.04264/) (2021)
- [A Study of the Attention Abnormality in Trojaned BERTs](https://mlsanity.com/paper/2205.08305/) (2022)
- [A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction](https://mlsanity.com/paper/2208.10240/) (2022)
- [Towards Robust Ranker for Text Retrieval](https://mlsanity.com/paper/2206.08063/) (2022)
- [ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models](https://mlsanity.com/paper/2110.11960/) (2021)
- [Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision](https://mlsanity.com/paper/2203.03762/) (2022)
- [TopoTxR: A Topological Biomarker for Predicting Treatment Response in Breast Cancer](https://mlsanity.com/paper/2105.06049/) (2021)
- [BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning](https://mlsanity.com/paper/2304.03144/) (2023)
- [Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation](https://mlsanity.com/paper/2208.09779/) (2022)
- [Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy](https://mlsanity.com/paper/2104.12041/) (2021)
- [DeepMTL Pro: Deep Learning Based MultipleTransmitter Localization and Power Estimation](https://mlsanity.com/paper/2112.13181/) (2021)
- [OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning](https://mlsanity.com/paper/2107.05252/) (2021)
- [FineEHR: Refine Clinical Note Representations to Improve Mortality Prediction](https://mlsanity.com/paper/2304.11794/) (2023)
- [Transfer Learning for Scientific Data Chain Extraction in Small Chemical Corpus with BERT-CRF Model](https://mlsanity.com/paper/1905.05615/) (2019)
- [Comprehensive evaluation of Mal-API-2019 dataset by machine learning in malware detection](https://mlsanity.com/paper/2403.02232/) (2024)

## Built on by (most cited first, 23 of 23)

- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- ["Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models](https://mlsanity.com/paper/2406.19417/) (2024)
- [TrojVLM: Backdoor Attack Against Vision Language Models](https://mlsanity.com/paper/2409.19232/) (2024)
- [textitAgents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks](https://mlsanity.com/paper/2504.00218/) (2025)
- [Backdooring Vision-Language Models with Out-Of-Distribution Data](https://mlsanity.com/paper/2410.01264/) (2024)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization](https://mlsanity.com/paper/2407.04118/) (2024)
- [InsectMamba: Insect Pest Classification with State Space Model](https://mlsanity.com/paper/2404.03611/) (2024)
- [A Study of Backdoors in Instruction Fine-tuned Language Models](https://mlsanity.com/paper/2406.07778/) (2024)
- [Research on Driver Facial Fatigue Detection Based on Yolov8 Model](https://mlsanity.com/paper/2406.18575/) (2024)
- [Data Augmentation for Image Classification using Generative AI](https://mlsanity.com/paper/2409.00547/) (2024)
- [Hummer: Towards Limited Competitive Preference Dataset](https://mlsanity.com/paper/2405.11647/) (2024)
- [Optimizing Search Advertising Strategies: Integrating Reinforcement Learning with Generalized Second-Price Auctions for Enhanced Ad Ranking and Bidding](https://mlsanity.com/paper/2405.13381/) (2024)
- [Deep Learning in Medical Image Classification from MRI-based Brain Tumor Images](https://mlsanity.com/paper/2408.00636/) (2024)
- [DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models](https://mlsanity.com/paper/2504.18053/) (2025)
- [BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Records](https://mlsanity.com/paper/2407.05213/) (2024)
- [Credit Risk Identification in Supply Chains Using Generative Adversarial Networks](https://mlsanity.com/paper/2501.10348/) (2025)
- [Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities](https://mlsanity.com/paper/2409.10764/) (2024)
- [A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective, Direction and Open Research Scopes](https://mlsanity.com/paper/2407.08839/) (2024)
- [Analyzing Multi-Head Attention on Trojan BERT Models](https://mlsanity.com/paper/2406.16925/) (2024)
- [Inverting Trojans in LLMs](https://mlsanity.com/paper/2509.16203/) (2025)
- [CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs](https://mlsanity.com/paper/2606.31309/) (2026)
- [Backdoor Learning in Language Models and Vision-Language Models](https://mlsanity.com/paper/2608.18095/) (2026)

## Abstract (arXiv)

Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence classification, struggling with tasks like question answering and named entity recognition. We introduce TABDet (Task-Agnostic Backdoor Detector), a pioneering task-agnostic method for backdoor detection. TABDet leverages final layer logits combined with an efficient pooling technique, enabling unified logit representation across three prominent NLP tasks. TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional task-specific methods.