Sebastian Rust
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sebastian Rust has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Björn Scheuermann
Technical University of Darmstadt, Darmstadt, Germany
2 shared publications - Leonhard Balduf
Technical University of Darmstadt, Darmstadt, Germany
1 shared publication - Tobias Meuser
Technical University of Darmstadt, Darmstadt, Germany
1 shared publication
Latest Publications
- Open Access
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 126-132
Reset the Stream, Keep the Keyframe: Partial Reliability for Media over QUIC Delivery Timeouts
Media over QUIC (MoQ) is the IETF's emerging transport for low-latency live video over QUIC. It carries video as a sequence of groups, each a keyframe followed by the frames that depend on it. To keep subscribers near the live edge, a relay drops media that grows too old by resetting the underlying QUIC stream with RESET_STREAM; if the keyframe was only partially delivered, the whole group becomes undecodable. The recent RESET_STREAM_AT QUIC extension instead allows a partial reset that preserves a reliable prefix of the stream, but Media over QUIC (MoQ) does not specify where to place that boundary. We propose two RESET_STREAM_AT placement strategies, protecting the keyframe or the last fully written object, and evaluate them against RESET_STREAM and a fully reliable baseline under lossy, congested, and combined conditions. RESET_STREAM_AT preserves all keyframes at no significant latency cost; RESET_STREAM's lower apparent keyframe latency is an artifact of averaging only the keyframes it delivered, omitting the ones it lost. The two also differ in stall behavior: RESET_STREAM risks multi-second freezes from consecutive keyframe loss, whereas RESET_STREAM_AT bounds each stall to roughly the duration of a single group.
- 20 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 126-132
Open AccessReset the Stream, Keep the Keyframe: Partial Reliability for Media over QUIC Delivery Timeouts
Media over QUIC (MoQ) is the IETF's emerging transport for low-latency live video over QUIC. It carries video as a sequence of groups, each a keyframe followed by the frames that depend on it. To keep subscribers near the live edge, a relay drops media that grows too old by resetting the underlying QUIC stream with RESET_STREAM; if the keyframe was only partially delivered, the whole group becomes undecodable. The recent RESET_STREAM_AT QUIC extension instead allows a partial reset that preserves a reliable prefix of the stream, but Media over QUIC (MoQ) does not specify where to place that boundary. We propose two RESET_STREAM_AT placement strategies, protecting the keyframe or the last fully written object, and evaluate them against RESET_STREAM and a fully reliable baseline under lossy, congested, and combined conditions. RESET_STREAM_AT preserves all keyframes at no significant latency cost; RESET_STREAM's lower apparent keyframe latency is an artifact of averaging only the keyframes it delivered, omitting the ones it lost. The two also differ in stall behavior: RESET_STREAM risks multi-second freezes from consecutive keyframe loss, whereas RESET_STREAM_AT bounds each stall to roughly the duration of a single group.
- Open Access
- 11 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 13-18
I'm InterPlanetary, Get Me Out of Here!
We investigate how well IPFS functions in real-world restrictive network environments. In a series of experiments, we utilize four vantage points, one of which lies behind the Great Firewall of China (GFW), to ascertain how various parts of the IPFS ecosystem perform in these settings. We test HTTP gateways and find that, although they are not systematically blocked, only about a third function in China, in comparison to Germany. Evaluating P2P functionality, we run experiments on data exchange between the four nodes. We find that the GFW has little measurable impact on these functionalities. The main inhibiting factor for P2P functionality remains network address translation (NAT). Lastly, to help NATed nodes spread their content, we propose and evaluate using public gateways as temporary replicators, but find only marginal gains.
- 11 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 13-18
Open AccessI'm InterPlanetary, Get Me Out of Here!
We investigate how well IPFS functions in real-world restrictive network environments. In a series of experiments, we utilize four vantage points, one of which lies behind the Great Firewall of China (GFW), to ascertain how various parts of the IPFS ecosystem perform in these settings. We test HTTP gateways and find that, although they are not systematically blocked, only about a third function in China, in comparison to Germany. Evaluating P2P functionality, we run experiments on data exchange between the four nodes. We find that the GFW has little measurable impact on these functionalities. The main inhibiting factor for P2P functionality remains network address translation (NAT). Lastly, to help NATed nodes spread their content, we propose and evaluate using public gateways as temporary replicators, but find only marginal gains.