Search

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into four major categories: optimization-based attacks such as Greedy Coordinate Gradient (GCG), jailbreak template-based attacks such as "Do-Anything-Now", advanced indirect attacks like DrAttack, and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delay to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM defense instance to concurrently protect the target LLM instance in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs (both target and defense LLMs) have the capability to identify harmful prompts or intentions in user queries, which we empirically validate using the commonly used GPT-3.5/4 models across all major jailbreak attacks. Our measurements show that SelfDefend enables GPT-3.5 to suppress the attack success rate (ASR) by 8.97-95.74% (average: 60%) and GPT-4 by even 36.36-100% (average: 83%), while incurring negligible effects on normal queries. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. These models outperform four SOTA defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. We also empirically show that the tuned models are robust to targeted GCG and prompt injection attacks., Comment: This paper completes its earlier vision paper, available at arXiv:2402.15727

Radio Frequency Identification (RFID) is a key technology used in many applications. In the past decades, plenty of secure and privacy-preserving RFID tag/mutual authentication protocols as well as formal frameworks for evaluating them have been proposed. However, we notice that a property, namely proof of possession (PoP), has not been rigorously studied till now, despite it has significant value in many RFID applications. For example, in RFID-enabled supply chains, PoP helps prevent dis-honest parties from publishing information about products/tags that they actually have never processed. We propose the first formal framework for RFID tag/mutual authentication with PoP after correcting deficiencies of some existing RFID formal frameworks. We provide a generic construction to transform an RFID tag/mutual authentication protocol to one that supports PoP using a cryptographic hash function, a pseudorandom function (PRF) and a signature scheme. We prove that the constructed protocol is secure and privacy-preserving under our framework if all the building blocks possess desired security properties. Finally, we show an RFID mutual authentication protocol with PoP. Arming tag/mutual authentication protocols with PoP is an important step to strengthen RFID-enabled systems as it bridges the security gap between physical layer and data layer, and reduces the misuses of RFID-related data.

Blockchain rewriting with fine-grained access control allows a user to create a transaction associated with a set of attributes, while another user (or modifier) who possesses enough rewriting privileges from a trusted authority satisfying the attribute set can rewrite the transaction. However, it lacks accountability and is not designed for open blockchains that require no trust assumptions. In this work, we introduce accountable fine-grained blockchain rewriting in a permissionless setting. The property of accountability allows the modifier's identity and her rewriting privileges to be held accountable for the modified transactions in case of malicious rewriting (e.g., modify the registered content from good to bad). We first present a generic framework to secure blockchain rewriting in the permissionless setting. Second, we present an instantiation of our approach and show its practicality through evaluation analysis. Last, we demonstrate that our proof-of-concept implementation can be effectively integrated into open blockchains., Comment: Under submission

Due to the wide use of highly-valuable and large-scale deep neural networks (DNNs), it becomes crucial to protect the intellectual property of DNNs so that the ownership of disputed or stolen DNNs can be verified. Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs. However, such solutions are vulnerable to model fine-tuning and pruning. They also suffer from fraudulent ownership claim as attackers can discover adversarial samples and use them as secret inputs to trigger distinguishable behaviors from stolen models. To address these problems, we propose a novel DNN watermarking solution, named HufuNet, for protecting the ownership of DNN models. We evaluate HufuNet rigorously on four benchmark datasets with five popular DNN models, including convolutional neural network (CNN) and recurrent neural network (RNN). The experiments demonstrate HufuNet is highly robust against model fine-tuning/pruning, kernels cutoff/supplement, functionality-equivalent attack, and fraudulent ownership claims, thus highly promising to protect large-scale DNN models in the real-world.

The popularity of smartphones has led to the growth of mobile app markets, creating a need for enhanced transparency, global access, and secure downloading. This paper introduces AGChain, a blockchain-based gateway that enables trustworthy app delegation within existing markets. AGChain ensures that markets can continue providing services while users benefit from permanent, distributed, and secure app delegation. During its development, we address two key challenges: significantly reducing smart contract gas costs and enabling fully distributed IPFS-based file storage. Additionally, we tackle three system issues related to security and sustainability. We have implemented a prototype of AGChain on Ethereum and Polygon blockchains, achieving effective security and decentralization with a minimal gas cost of around 0.002 USD per app upload (no cost for app download). The system also exhibits reasonable performance with an average overhead of 12%., Comment: This is a technical report submitted to the Special Issue of the Elsevier Journal of Systems Architecture (JSA)

Strong passwords are fundamental to the security of password-based user authentication systems. In recent years, much effort has been made to evaluate password strength or to generate strong passwords. Unfortunately, the usability or memorability of the strong passwords has been largely neglected. In this paper, we aim to bridge the gap between strong password generation and the usability of strong passwords. We propose to automatically generate textual password mnemonics, i.e., natural language sentences, which are intended to help users better memorize passwords. We introduce \textit{DeepMnemonic}, a deep attentive encoder-decoder framework which takes a password as input and then automatically generates a mnemonic sentence for the password. We conduct extensive experiments to evaluate DeepMnemonic on the real-world data sets. The experimental results demonstrate that DeepMnemonic outperforms a well-known baseline for generating semantically meaningful mnemonic sentences. Moreover, the user study further validates that the generated mnemonic sentences by DeepMnemonic are useful in helping users memorize strong passwords., Comment: Published in IEEE Transactions on Dependable and Secure Computing (TDSC)

This paper proposes the first user-independent inter-keystroke timing attacks on PINs. Our attack method is based on an inter-keystroke timing dictionary built from a human cognitive model whose parameters can be determined by a small amount of training data on any users (not necessarily the target victims). Our attacks can thus be potentially launched on a large scale in real-world settings. We investigate inter-keystroke timing attacks in different online attack settings and evaluate their performance on PINs at different strength levels. Our experimental results show that the proposed attack performs significantly better than random guessing attacks. We further demonstrate that our attacks pose a serious threat to real-world applications and propose various ways to mitigate the threat., Comment: 16 pages, 9 figures

Validating network paths taken by packets is critical for a secure Internet architecture. Any feasible solution must both enforce packet forwarding along endhost-specified paths and verify whether packets have taken those paths. However, neither enforcement nor verification is supported by the current Internet. Due likely to a long-standing confusion between routing and forwarding, only limited solutions for path validation exist in the literature. This survey article aims to reinvigorate research in to the significant and essential topic of path validation. It crystallizes not only how path validation works but also where seemingly qualified solutions fall short. The analyses explore future research directions in path validation toward improving security, privacy, and efficiency., Comment: 30 pages with 5 figures, submitted to ACM Computing Surveys

Cross-app collaboration via inter-component communication is a fundamental mechanism on Android. Although it brings the benefits such as functionality reuse and data sharing, a threat called component hijacking is also introduced. By hijacking a vulnerable component in victim apps, an attack app can escalate its privilege for operations originally prohibited. Many prior studies have been performed to understand and mitigate this issue, but no defense is being deployed in the wild, largely due to the deployment difficulties and performance concerns. In this paper we present SCLib, a secure component library that performs in-app mandatory access control on behalf of app components. It does not require firmware modification or app repackaging as in previous works. The library-based nature also makes SCLib more accessible to app developers, and enables them produce secure components in the first place over fragmented Android devices. As a proof of concept, we design six mandatory policies and overcome unique implementation challenges to mitigate attacks originated from both system weaknesses and common developer mistakes. Our evaluation using ten high-profile open source apps shows that SCLib can protect their 35 risky components with negligible code footprint (less than 0.3% stub code) and nearly no slowdown to normal intra-app communications. The worst-case performance overhead to stop attacks is about 5%., Comment: This is the extended technical report version of our SCLib paper accepted by ACM CODASPY 2018 (http://www.ycheng.org/codaspy/2018/accepted.html)

Cross-app collaboration via inter-component communication is a fundamental mechanism on Android. Although it brings the benefits such as functionality reuse and data sharing, a threat called component hijacking is also introduced. By hijacking a vulnerable component in victim apps, an attack app can escalate its privilege for originally prohibited operations. Many prior studies have been performed to understand and mitigate this issue, but component hijacking remains a serious open problem in the Android ecosystem due to no effective defense deployed in the wild. In this paper, we present our vision on practically defending against component hijacking in Android apps. First, we argue that to fundamentally prevent component hijacking, we need to switch from the previous mindset (i.e., performing system-level control or repackaging vulnerable apps after they are already released) to a more proactive version that aims to help security-inexperienced developers make secure components in the first place. To this end, we propose to embed into apps a secure component library (SecComp), which performs in-app mandatory access control on behalf of app components. An important factor for SecComp to be effective is that we find it is possible to devise a set of practical in-app policies to stop component hijacking. Furthermore, we allow developers design custom policies, beyond our by-default generic policies, to support more fine-grained access control. We have overcome challenges to implement a preliminary SecComp prototype, which stops component hijacking with very low performance overhead. We hope the future research that fully implements our vision can eventually help real-world apps get rid of component hijacking., Comment: This is a technical report on Android security from Singapore Management University

The EPCglobal network is a computer network which allows supply chain companies to search for their unknown partners globally and share information stored in product RFID tags with each other. Although there have been quite a number of recent research works done to improve the security of EPCglobal Network, the existing access control solutions are not efficient and scalable. For instance, when a user queries Electronic Product Code Information Service (EPCIS) for EPC event information, the EPCIS would have to query the Electronic Product Code Discovery Service (EPCDS) to check the access rights of the user. This implementation is not efficient and creates a bottleneck at EPCDS. In this paper, we design and propose a digital signature scheme, SignEPC, as a more efficient and scalable access control solution for EPCglobal network. Our paper will also evaluate SignEPC by considering the various possible attacks that could be done on our proposed model