No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models

To reduce the computation cost and the energy consumption in large language models (LLM), skimming-based acceleration dynamically drops unimportant tokens of the input sequence progressively along layers of the LLM while preserving the tokens of semantic importance. However, our work for the first time reveals the acceleration may be vulnerable to Denial-of-Service (DoS) attacks. In this paper, we propose No-Skim, a general framework to help the owners of skimming-based LLM to understand and measure the robustness of their acceleration scheme. Specifically, our framework searches minimal and unnoticeable perturbations at character-level and token-level to generate adversarial inputs that sufficiently increase the remaining token ratio, thus increasing the computation cost and energy consumption. We systematically evaluate the vulnerability of the skimming acceleration in various LLM architectures including BERT and RoBERTa on the GLUE benchmark. In the worst case, the perturbation found by No-Skim substantially increases the running cost of LLM by over 145% on average. Moreover, No-Skim extends the evaluation framework to various scenarios, making the evaluation conductible with different level of knowledge.

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting

Deep neural networks (DNNs) are susceptible to backdoor attacks, where malicious functionality is embedded to allow attackers to trigger incorrect classifications. Old-school backdoor attacks use strong trigger features that can easily be learned by victim models. Despite robustness against input variation, the robustness however increases the likelihood of unintentional trigger activations. This leaves traces to existing defenses, which find approximate replacements for the original triggers that can activate the backdoor without being identical to the original trigger via, e.g., reverse engineering and sample overlay. In this paper, we propose and investigate a new characteristic of backdoor attacks, namely, backdoor exclusivity, which measures the ability of backdoor triggers to remain effective in the presence of input variation. Building upon the concept of backdoor exclusivity, we propose Backdoor Exclusivity LifTing (BELT), a novel technique which suppresses the association between the backdoor and fuzzy triggers to enhance backdoor exclusivity for defense evasion. Extensive evaluation on three popular backdoor benchmarks validate, our approach substantially enhances the stealthiness of four old-school backdoor attacks, which, after backdoor exclusivity lifting, is able to evade six state-of-the-art backdoor countermeasures, at almost no cost of the attack success rate and normal utility. For example, one of the earliest backdoor attacks BadNet, enhanced by BELT, evades most of the state-of-the-art defenses including ABS and MOTH which would otherwise recognize the backdoored model.

JADE: A Linguistics-based Safety Evaluation Platform for LLM

In this paper, we present JADE, a targeted linguistic fuzzing platform which strengthens the linguistic complexity of seed questions to simultaneously and consistently break a wide range of widely-used LLMs categorized in three groups: eight open-sourced Chinese, six commercial Chinese and four commercial English LLMs. JADE generates three safety benchmarks for the three groups of LLMs, which contain unsafe questions that are highly threatening: the questions simultaneously trigger harmful generation of multiple LLMs, with an average unsafe generation ratio of $70\%$ (please see the table below), while are still natural questions, fluent and preserving the core unsafe semantics. We release the benchmark demos generated for commercial English LLMs and open-sourced English LLMs in the following link: https://github.com/whitzard-ai/jade-db. For readers who are interested in evaluating on more questions generated by JADE, please contact us. JADE is based on Noam Chomsky's seminal theory of transformational-generative grammar. Given a seed question with unsafe intention, JADE invokes a sequence of generative and transformational rules to increment the complexity of the syntactic structure of the original question, until the safety guardrail is broken. Our key insight is: Due to the complexity of human language, most of the current best LLMs can hardly recognize the invariant evil from the infinite number of different syntactic structures which form an unbound example space that can never be fully covered. Technically, the generative/transformative rules are constructed by native speakers of the languages, and, once developed, can be used to automatically grow and transform the parse tree of a given question, until the guardrail is broken. For more evaluation results and demo, please check our website: https://whitzard-ai.github.io/jade.html.

MIRA: Cracking Black-box Watermarking on Deep Neural Networks via Model Inversion-based Removal Attacks

To protect the intellectual property of well-trained deep neural networks (DNNs), black-box DNN watermarks, which are embedded into the prediction behavior of DNN models on a set of specially-crafted samples, have gained increasing popularity in both academy and industry. Watermark robustness is usually implemented against attackers who steal the protected model and obfuscate its parameters for watermark removal. Recent studies empirically prove the robustness of most black-box watermarking schemes against known removal attempts. In this paper, we propose a novel Model Inversion-based Removal Attack (\textsc{Mira}), which is watermark-agnostic and effective against most of mainstream black-box DNN watermarking schemes. In general, our attack pipeline exploits the internals of the protected model to recover and unlearn the watermark message. We further design target class detection and recovered sample splitting algorithms to reduce the utility loss caused by \textsc{Mira} and achieve data-free watermark removal on half of the watermarking schemes. We conduct comprehensive evaluation of \textsc{Mira} against ten mainstream black-box watermarks on three benchmark datasets and DNN architectures. Compared with six baseline removal attacks, \textsc{Mira} achieves strong watermark removal effects on the covered watermarks, preserving at least $90\%$ of the stolen model utility, under more relaxed or even no assumptions on the dataset availability.

Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation

Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the prediction behaviors or the model internals. Sacrificing less functionality and involving more knowledge about the target DNN, the latter branch called \textit{white-box DNN watermarking} is believed to be accurate, credible and secure against most known watermark removal attacks, with emerging research efforts in both the academy and the industry. In this paper, we present the first systematic study on how the mainstream white-box DNN watermarks are commonly vulnerable to neural structural obfuscation with \textit{dummy neurons}, a group of neurons which can be added to a target model but leave the model behavior invariant. Devising a comprehensive framework to automatically generate and inject dummy neurons with high stealthiness, our novel attack intensively modifies the architecture of the target model to inhibit the success of watermark verification. With extensive evaluation, our work for the first time shows that nine published watermarking schemes require amendments to their verification procedures.

Exorcising ''Wraith'': Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attacks

Automated driving systems rely on 3D object detectors to recognize possible obstacles from LiDAR point clouds. However, recent works show the adversary can forge non-existent cars in the prediction results with a few fake points (i.e., appearing attack). By removing statistical outliers, existing defenses are however designed for specific attacks or biased by predefined heuristic rules. Towards more comprehensive mitigation, we first systematically inspect the mechanism of recent appearing attacks: Their common weaknesses are observed in crafting fake obstacles which (i) have obvious differences in the local parts compared with real obstacles and (ii) violate the physical relation between depth and point density. In this paper, we propose a novel plug-and-play defensive module which works by side of a trained LiDAR-based object detector to eliminate forged obstacles where a major proportion of local parts have low objectness, i.e., to what degree it belongs to a real object. At the core of our module is a local objectness predictor, which explicitly incorporates the depth information to model the relation between depth and point density, and predicts each local part of an obstacle with an objectness score. Extensive experiments show, our proposed defense eliminates at least 70% cars forged by three known appearing attacks in most cases, while, for the best previous defense, less than 30% forged cars are eliminated. Meanwhile, under the same circumstance, our defense incurs less overhead for AP/precision on cars compared with existing defenses. Furthermore, We validate the effectiveness of our proposed defense on simulation-based closed-loop control driving tests in the open-source system of Baidu's Apollo.

A Certifiable Security Patch for Object Tracking in Self-Driving Systems via Historical Deviation Modeling

Self-driving cars (SDC) commonly implement the perception pipeline to detect the surrounding obstacles and track their moving trajectories, which lays the ground for the subsequent driving decision making process. Although the security of obstacle detection in SDC is intensively studied, not until very recently the attackers start to exploit the vulnerability of the tracking module. Compared with solely attacking the object detectors, this new attack strategy influences the driving decision more effectively with less attack budgets. However, little is known on whether the revealed vulnerability remains effective in end-to-end self-driving systems and, if so, how to mitigate the threat. In this paper, we present the first systematic research on the security of object tracking in SDC. Through a comprehensive case study on the full perception pipeline of a popular open-sourced self-driving system, Baidu's Apollo, we prove the mainstream multi-object tracker (MOT) based on Kalman Filter (KF) is unsafe even with an enabled multi-sensor fusion mechanism. Our root cause analysis reveals, the vulnerability is innate to the design of KF-based MOT, which shall error-handle the prediction results from the object detectors yet the adopted KF algorithm is prone to trust the observation more when its deviation from the prediction is larger. To address this design flaw, we propose a simple yet effective security patch for KF-based MOT, the core of which is an adaptive strategy to balance the focus of KF on observations and predictions according to the anomaly index of the observation-prediction deviation, and has certified effectiveness against a generalized hijacking attack model. Extensive evaluation on $4$ KF-based existing MOT implementations (including 2D and 3D, academic and Apollo ones) validate the defense effectiveness and the trivial performance overhead of our approach.

Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model

In this paper, we present a novel insider attack called Matryoshka, which employs an irrelevant scheduled-to-publish DNN model as a carrier model for covert transmission of multiple secret models which memorize the functionality of private ML data stored in local data centers. Instead of treating the parameters of the carrier model as bit strings and applying conventional steganography, we devise a novel parameter sharing approach which exploits the learning capacity of the carrier model for information hiding. Matryoshka simultaneously achieves: (i) High Capacity -- With almost no utility loss of the carrier model, Matryoshka can hide a 26x larger secret model or 8 secret models of diverse architectures spanning different application domains in the carrier model, neither of which can be done with existing steganography techniques; (ii) Decoding Efficiency -- once downloading the published carrier model, an outside colluder can exclusively decode the hidden models from the carrier model with only several integer secrets and the knowledge of the hidden model architecture; (iii) Effectiveness -- Moreover, almost all the recovered models have similar performance as if it were trained independently on the private data; (iv) Robustness -- Information redundancy is naturally implemented to achieve resilience against common post-processing techniques on the carrier before its publishing; (v) Covertness -- A model inspector with different levels of prior knowledge could hardly differentiate a carrier model from a normal model.

Cracking White-box DNN Watermarks via Invariant Neuron Transforms

Recently, how to protect the Intellectual Property (IP) of deep neural networks (DNN) becomes a major concern for the AI industry. To combat potential model piracy, recent works explore various watermarking strategies to embed secret identity messages into the prediction behaviors or the internals (e.g., weights and neuron activation) of the target model. Sacrificing less functionality and involving more knowledge about the target model, the latter branch of watermarking schemes (i.e., white-box model watermarking) is claimed to be accurate, credible and secure against most known watermark removal attacks, with emerging research efforts and applications in the industry. In this paper, we present the first effective removal attack which cracks almost all the existing white-box watermarking schemes with provably no performance overhead and no required prior knowledge. By analyzing these IP protection mechanisms at the granularity of neurons, we for the first time discover their common dependence on a set of fragile features of a local neuron group, all of which can be arbitrarily tampered by our proposed chain of invariant neuron transforms. On $9$ state-of-the-art white-box watermarking schemes and a broad set of industry-level DNN architectures, our attack for the first time reduces the embedded identity message in the protected models to be almost random. Meanwhile, unlike known removal attacks, our attack requires no prior knowledge on the training data distribution or the adopted watermark algorithms, and leaves model functionality intact.

"And Then There Were None": Cracking White-box DNN Watermarks via Invariant Neuron Transforms

Recently, how to protect the Intellectual Property (IP) of deep neural networks (DNN) becomes a major concern for the AI industry. To combat potential model piracy, recent works explore various watermarking strategies to embed secret identity messages into the prediction behaviors or the internals (e.g., weights and neuron activation) of the target model. Sacrificing less functionality and involving more knowledge about the target model, the latter branch of watermarking schemes (i.e., white-box model watermarking) is claimed to be accurate, credible and secure against most known watermark removal attacks, with emerging research efforts and applications in the industry. In this paper, we present the first effective removal attack which cracks almost all the existing white-box watermarking schemes with provably no performance overhead and no required prior knowledge. By analyzing these IP protection mechanisms at the granularity of neurons, we for the first time discover their common dependence on a set of fragile features of a local neuron group, all of which can be arbitrarily tampered by our proposed chain of invariant neuron transforms. On $9$ state-of-the-art white-box watermarking schemes and a broad set of industry-level DNN architectures, our attack for the first time reduces the embedded identity message in the protected models to be almost random. Meanwhile, unlike known removal attacks, our attack requires no prior knowledge on the training data distribution or the adopted watermark algorithms, and leaves model functionality intact.