This work focuses on defending against the data poisoning based backdoor attacks, which bring in serious security threats to deep neural networks (DNNs). Specifically, given a untrustworthy training dataset, we aim to filter out potential poisoned samples, \ie, poisoned sample detection (PSD). The key solution for this task is to find a discriminative metric between clean and poisoned samples, even though there is no information about the potential poisoned samples (\eg, the attack method, the poisoning ratio). In this work, we develop an innovative detection approach from the perspective of the gradient \wrt activation (\ie, activation gradient direction, AGD) of each sample in the backdoored model trained on the untrustworthy dataset. We present an interesting observation that the circular distribution of AGDs among all samples of the target class is much more dispersed than that of one clean class. Motivated by this observation, we firstly design a novel metric called Cosine similarity Variation towards Basis Transition (CVBT) to measure the circular distribution's dispersion of each class. Then, we design a simple yet effective algorithm with identifying the target class(es) using outlier detection on CVBT scores of all classes, followed by progressively filtering of poisoned samples according to the cosine similarities of AGDs between every potential sample and a few additional clean samples. Extensive experiments under various settings verify that given very few clean samples of each class, the proposed method could filter out most poisoned samples, while avoiding filtering out clean samples, verifying its effectiveness on the PSD task. Codes are available at //github.com/SCLBD/bdzoo2/blob/dev/detection_pretrain/agpd.py.
相關內容
Due to the data imbalance and the diversity of defects, student-teacher networks (S-T) are favored in unsupervised anomaly detection, which explores the discrepancy in feature representation derived from the knowledge distillation process to recognize anomalies. However, vanilla S-T network is not stable. Employing identical structures to construct the S-T network may weaken the representative discrepancy on anomalies. But using different structures can increase the likelihood of divergent performance on normal data. To address this problem, we propose a novel dual-student knowledge distillation (DSKD) architecture. Different from other S-T networks, we use two student networks a single pre-trained teacher network, where the students have the same scale but inverted structures. This framework can enhance the distillation effect to improve the consistency in recognition of normal data, and simultaneously introduce diversity for anomaly representation. To explore high-dimensional semantic information to capture anomaly clues, we employ two strategies. First, a pyramid matching mode is used to perform knowledge distillation on multi-scale feature maps in the intermediate layers of networks. Second, an interaction is facilitated between the two student networks through a deep feature embedding module, which is inspired by real-world group discussions. In terms of classification, we obtain pixel-wise anomaly segmentation maps by measuring the discrepancy between the output feature maps of the teacher and student networks, from which an anomaly score is computed for sample-wise determination. We evaluate DSKD on three benchmark datasets and probe the effects of internal modules through ablation experiments. The results demonstrate that DSKD can achieve exceptional performance on small models like ResNet18 and effectively improve vanilla S-T networks.
Modern software often struggles with bloat, leading to increased memory consumption and security vulnerabilities from unused code. In response, various program debloating techniques have been developed, typically utilizing test cases that represent functionalities users want to retain. These methods range from aggressive approaches, which prioritize maximal code reduction but may overfit to test cases and potentially reintroduce past security issues, to conservative strategies that aim to preserve all influenced code, often at the expense of less effective bloat reduction and security improvement. In this research, we present RLDebloatDU, an innovative debloating technique that employs 1-DU chain minimality within abstract syntax trees. Our approach maintains essential program data dependencies, striking a balance between aggressive code reduction and the preservation of program semantics. We evaluated RLDebloatDU on ten Linux kernel programs, comparing its performance with two leading debloating techniques: Chisel, known for its aggressive debloating approach, and Razor, recognized for its conservative strategy. RLDebloatDU significantly lowers the incidence of Common Vulnerabilities and Exposures (CVEs) and improves soundness compared to both, highlighting its efficacy in reducing security issues without reintroducing resolved security issues.
Much of the research in differential privacy has focused on offline applications with the assumption that all data is available at once. When these algorithms are applied in practice to streams where data is collected over time, this either violates the privacy guarantees or results in poor utility. We derive an algorithm for differentially private synthetic streaming data generation, especially curated towards spatial datasets. Furthermore, we provide a general framework for online selective counting among a collection of queries which forms a basis for many tasks such as query answering and synthetic data generation. The utility of our algorithm is verified on both real-world and simulated datasets.
Modern SMT solvers, such as Z3, offer user-controllable strategies, enabling users to tailor them for their unique set of instances, thus dramatically enhancing solver performance for their use case. However, this approach of strategy customization presents a significant challenge: handcrafting an optimized strategy for a class of SMT instances remains a complex and demanding task for both solver developers and users alike. In this paper, we address this problem of automatic SMT strategy synthesis via a novel Monte Carlo Tree Search (MCTS) based method. Our method treats strategy synthesis as a sequential decision-making process, whose search tree corresponds to the strategy space, and employs MCTS to navigate this vast search space. The key innovations that enable our method to identify effective strategies, while keeping costs low, are the ideas of layered and staged MCTS search. These novel approaches allow for a deeper and more efficient exploration of the strategy space, enabling us to synthesize more effective strategies than the default ones in state-of-the-art (SOTA) SMT solvers. We implement our method, dubbed Z3alpha, as part of the Z3 SMT solver. Through extensive evaluations across 6 important SMT logics, Z3alpha demonstrates superior performance compared to the SOTA synthesis tool FastSMT, the default Z3 solver, and the CVC5 solver on most benchmarks. Remarkably, on a challenging QF_BV benchmark set, Z3alpha solves 42.7% more instances than the default strategy in the Z3 SMT solver.
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come from two aspects: 1) agents in imitation learning are usually implemented as deep neural networks, which are black-box models and lack interpretability; 2) the latent causal mechanism behind agents' decisions may vary along the trajectory, rather than staying static throughout time steps. To increase transparency and offer better interpretability of the neural agent, we propose to expose its captured knowledge in the form of a directed acyclic causal graph, with nodes being action and state variables and edges denoting the causal relations behind predictions. Furthermore, we design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. Concretely, we conduct causal discovery from the perspective of Granger causality and propose a self-explainable imitation learning framework, {\method}. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner. After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed {\method} in learning the dynamic causal graphs for understanding the decision-making of imitation learning meanwhile maintaining high prediction accuracy.
Proactivity in robot assistance refers to the robot's ability to anticipate user needs and perform assistive actions without explicit requests. This requires understanding user routines, predicting consistent activities, and actively seeking information to predict inconsistent behaviors. We propose SLaTe-PRO (Sequential Latent Temporal model for Predicting Routine Object usage), which improves upon prior state-of-the-art by combining object and user action information, and conditioning object usage predictions on past history. Additionally, we find some human behavior to be inherently stochastic and lacking in contextual cues that the robot can use for proactive assistance. To address such cases, we introduce an interactive query mechanism that can be used to ask queries about the user's intended activities and object use to improve prediction. We evaluate our approach on longitudinal data from three households, spanning 24 activity classes. SLaTe-PRO performance raises the F1 score metric to 0.57 without queries, and 0.60 with user queries, over a score of 0.43 from prior work. We additionally present a case study with a fully autonomous household robot.
We show that a distributed network of robots or other devices which make measurements of each other can collaborate to globally localise via efficient ad-hoc peer to peer communication. Our Robot Web solution is based on Gaussian Belief Propagation on the fundamental non-linear factor graph describing the probabilistic structure of all of the observations robots make internally or of each other, and is flexible for any type of robot, motion or sensor. We define a simple and efficient communication protocol which can be implemented by the publishing and reading of web pages or other asynchronous communication technologies. We show in simulations with up to 1000 robots interacting in arbitrary patterns that our solution convergently achieves global accuracy as accurate as a centralised non-linear factor graph solver while operating with high distributed efficiency of computation and communication. Via the use of robust factors in GBP, our method is tolerant to a high percentage of faults in sensor measurements or dropped communication packets.
We investigate the potential of patent data for improving the antibody humanness prediction using a multi-stage, multi-loss training process. Humanness serves as a proxy for the immunogenic response to antibody therapeutics, one of the major causes of attrition in drug discovery and a challenging obstacle for their use in clinical settings. We pose the initial learning stage as a weakly-supervised contrastive-learning problem, where each antibody sequence is associated with possibly multiple identifiers of function and the objective is to learn an encoder that groups them according to their patented properties. We then freeze a part of the contrastive encoder and continue training it on the patent data using the cross-entropy loss to predict the humanness score of a given antibody sequence. We illustrate the utility of the patent data and our approach by performing inference on three different immunogenicity datasets, unseen during training. Our empirical results demonstrate that the learned model consistently outperforms the alternative baselines and establishes new state-of-the-art on five out of six inference tasks, irrespective of the used metric.
Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans, we recognize that robots do not need to explicitly model every low-level action another agent will make; instead, we can capture the latent strategy of other agents through high-level representations. We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. The ego agent then leverages these latent dynamics to influence the other agent, purposely guiding them towards policies suitable for co-adaptation. Across several simulated domains and a real-world air hockey game, our approach outperforms the alternatives and learns to influence the other agent.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191