# Differentiable Adversarial Attacks for Marked Temporal Point Processes

arXiv: https://arxiv.org/abs/2501.10606 · HTML: https://mlsanity.com/paper/2501.10606/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 17 Jan 2025.

## Builds on (most cited first, 27 of 27)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://mlsanity.com/paper/2302.03668/) (2023)
- [Automatically Auditing Large Language Models via Discrete Optimization](https://mlsanity.com/paper/2303.04381/) (2023)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [Fully Neural Network based Model for General Temporal Point Processes](https://mlsanity.com/paper/1905.09690/) (2019)
- [Neural Temporal Point Processes: A Review](https://mlsanity.com/paper/2104.03528/) (2021)
- [Structure Invariant Transformation for better Adversarial Transferability](https://mlsanity.com/paper/2309.14700/) (2023)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://mlsanity.com/paper/1903.07054/) (2019)
- [Identifying Coordinated Accounts on Social Media through Hidden Influence and Group Behaviours](https://mlsanity.com/paper/2008.11308/) (2020)
- [Wasserstein Learning of Deep Generative Point Process Models](https://mlsanity.com/paper/1705.08051/) (2017)
- [Adversarial Attacks on Time Series](https://mlsanity.com/paper/1902.10755/) (2019)
- [Transferable Adversarial Attack based on Integrated Gradients](https://mlsanity.com/paper/2205.13152/) (2022)
- [Fake News Mitigation via Point Process Based Intervention](https://mlsanity.com/paper/1703.07823/) (2017)
- [Self-Attentive Hawkes Processes](https://mlsanity.com/paper/1907.07561/) (2019)
- [Learning and Forecasting Opinion Dynamics in Social Networks](https://mlsanity.com/paper/1506.05474/) (2015)
- [Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences](https://mlsanity.com/paper/2202.11485/) (2022)
- [Region Invariant Normalizing Flows for Mobility Transfer](https://mlsanity.com/paper/2109.05738/) (2021)
- [Stochastic Optimal Control of Epidemic Processes in Networks](https://mlsanity.com/paper/1810.13043/) (2018)
- [Dynamic Time Warping based Adversarial Framework for Time-Series Domain](https://mlsanity.com/paper/2207.04308/) (2022)
- [Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks](https://mlsanity.com/paper/2112.14232/) (2021)

## Abstract (arXiv)

Marked temporal point processes (MTPPs) have been shown to be extremely effective in modeling continuous time event sequences (CTESs). In this work, we present adversarial attacks designed specifically for MTPP models. A key criterion for a good adversarial attack is its imperceptibility. For objects such as images or text, this is often achieved by bounding perturbation in some fixed Lp norm-ball. However, similarly minimizing distance norms between two CTESs in the context of MTPPs is challenging due to their sequential nature and varying time-scales and lengths. We address this challenge by first permuting the events and then incorporating the additive noise to the arrival timestamps. However, the worst case optimization of such adversarial attacks is a hard combinatorial problem, requiring exploration across a permutation space that is factorially large in the length of the input sequence. As a result, we propose a novel differentiable scheme PERMTPP using which we can perform adversarial attacks by learning to minimize the likelihood, while minimizing the distance between two CTESs. Our experiments on four real-world datasets demonstrate the offensive and defensive capabilities, and lower inference times of PERMTPP.