Search

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking", which induces the model to generate malicious responses against the usage policy and society by designing adversarial prompts. With the emergence of jailbreak attack methods exploiting different vulnerabilities in LLMs, the corresponding safety alignment measures are also evolving. In this paper, we propose a comprehensive and detailed taxonomy of jailbreak attack and defense methods. For instance, the attack methods are divided into black-box and white-box attacks based on the transparency of the target model. Meanwhile, we classify defense methods into prompt-level and model-level defenses. Additionally, we further subdivide these attack and defense methods into distinct sub-classes and present a coherent diagram illustrating their relationships. We also conduct an investigation into the current evaluation methods and compare them from different perspectives. Our findings aim to inspire future research and practical implementations in safeguarding LLMs against adversarial attacks. Above all, although jailbreak remains a significant concern within the community, we believe that our work enhances the understanding of this domain and provides a foundation for developing more secure LLMs.

The geostrophic turbulence in rapidly rotating thermal convection exhibits characteristics shared by many highly turbulent geophysical and astrophysical flows. In this regime, the convective length and velocity scales, heat flux, and kinetic and thermal dissipation rates are all diffusion-free, meaning that they are independent of the viscosity and thermal diffusivity. Our direct numerical simulations (DNS) of rotating Rayleigh--B\'enard convection in domains with no-slip top and bottom and periodic lateral boundary conditions for a fluid with the Prandtl number $Pr=1$ and extreme buoyancy and rotation parameters (the Rayleigh number up to $Ra=3\times10^{13}$ and the Ekman number down to $Ek=5\times10^{-9}$) indeed demonstrate these diffusion-free scaling relations, in particular, that the dimensionless convective heat transport scales with the supercriticality parameter $\widetilde{Ra}\equiv Ra\,Ek^{4/3}$ as $Nu-1\propto \widetilde{Ra}^{3/2}$, where $Nu$ is the Nusselt number. We further derive and verify in the DNS that with the decreasing $\widetilde{Ra}$ the geostrophic turbulence regime undergoes a transition into another geostrophic regime where the convective heat transport scales as $Nu-1\propto \widetilde{Ra}^{3}$., Comment: 13 pages, 3 figures

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in advertisement, recommender systems and many other applications. In these applications, sometimes the offline data is collected from multiple behavior policies. Previous works regard data from different behavior policies equally. Nevertheless, some behavior policies are better at producing good estimators while others are not. This paper starts with discussing how to correctly mix estimators produced by different behavior policies. We propose three ways to reduce the variance of the mixture estimator when all sub-estimators are unbiased or asymptotically unbiased. Furthermore, experiments on simulated recommender systems show that our methods are effective in reducing the Mean-Square Error of estimation., Comment: Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2020

IP protocol is the core of TCP/IP network layer. However, since IP address and its Domain Name are allocated and managed by a single agency, there are risks of centralization. The semantic overload of IP address also reduces its scalability and mobility, which further hinders the security. This paper proposes a co-governing Multi-Identifier Network (MIN) architecture that constructs a network layer with parallel coexistence of multiple identifiers, including identity, content, geographic information, and IP address. On the management plane, we develop an efficient management system using consortium blockchain with voting consensus, so the network can simultaneously manage and support by hundreds or thousands of nodes with high throughput. On the data plane, we propose an algorithm merging hash table and prefix tree (HTP) for FIB, which avoids the false-negative error and can inter-translate different identifiers with tens of billions of entries. Further, we propose a scheme to transport IP packets using CCN as a tunnel for supporting progressive deployment. We deployed the prototype of MIN to the largest operators' network in Mainland China, Hongkong and Macao, and demonstrated that the network can register identifier under co-governing consensus algorithm, support VoD service very well., Comment: 13 pages

The Internet has become the most important infrastructure of modern society, while the existing IP network is unable to provide high-quality service. The unilateralism IP network is unable to satisfy the Co-managing and Co-governing demands to Cyberspace for most Nations in the world as well. Facing this challenge, we propose a novel Decentralized Multilateral Co-Governing Post-IP Internet architecture. To verify its effectiveness, we develop the prototype on the operator's networks including China Mainland, Hong Kong, and Macao. The experiments and testing results show that this architecture is feasible for co-existing of Content-Centric Networking and IP network, and it might become a Chinese Solution to the world., Comment: 10 pages

Recommender systems play a crucial role in our daily lives. Feed streaming mechanism has been widely used in the recommender system, especially on the mobile Apps. The feed streaming setting provides users the interactive manner of recommendation in never-ending feeds. In such an interactive manner, a good recommender system should pay more attention to user stickiness, which is far beyond classical instant metrics, and typically measured by {\bf long-term user engagement}. Directly optimizing the long-term user engagement is a non-trivial problem, as the learning target is usually not available for conventional supervised learning methods. Though reinforcement learning~(RL) naturally fits the problem of maximizing the long term rewards, applying RL to optimize long-term user engagement is still facing challenges: user behaviors are versatile and difficult to model, which typically consists of both instant feedback~(e.g. clicks, ordering) and delayed feedback~(e.g. dwell time, revisit); in addition, performing effective off-policy learning is still immature, especially when combining bootstrapping and function approximation. To address these issues, in this work, we introduce a reinforcement learning framework --- FeedRec to optimize the long-term user engagement. FeedRec includes two components: 1)~a Q-Network which designed in hierarchical LSTM takes charge of modeling complex user behaviors, and 2)~an S-Network, which simulates the environment, assists the Q-Network and voids the instability of convergence in policy learning. Extensive experiments on synthetic data and a real-world large scale data show that FeedRec effectively optimizes the long-term user engagement and outperforms state-of-the-arts.